Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    places or scenarios related to specific contexts or settings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to societal norms and issues regarding marriage and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.02
    2:0.10
    3:0.10
    4:0.04
    5:0.13
    6:0.05
    7:0.09
    8:0.08
    9:0.04
    10:0.15
    11:0.08
    Negative Logits
    ��
    -0.96
    obin
    -0.95
    avez
    -0.91
    ��
    -0.91
    Malley
    -0.84
    berman
    -0.81
     ALS
    -0.78
     LLP
    -0.77
    imester
    -0.77
    bilt
    -0.76
    POSITIVE LOGITS
     existed
    0.85
     exists
    0.84
     goes
    0.83
     enters
    0.83
     mattered
    0.83
     belongs
    0.82
     survives
    0.79
     attaches
    0.77
     happens
    0.77
     came
    0.76
    Act Density 0.097%

    No Known Activations