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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate gatherings or group meetings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.07
    3:0.06
    4:0.15
    5:0.03
    6:0.05
    7:0.28
    8:0.03
    9:0.03
    10:0.12
    11:0.07
    Negative Logits
     trajectory
    -2.07
     switch
    -2.04
     turnaround
    -1.89
     improved
    -1.81
     workaround
    -1.78
     gradient
    -1.76
     switched
    -1.76
     traject
    -1.74
     adjustment
    -1.71
     gap
    -1.70
    POSITIVE LOGITS
    soever
    2.72
    Discussion
    2.07
     gatherings
    1.92
    Friends
    1.83
    Members
    1.81
    BLIC
    1.77
    idium
    1.74
    Ear
    1.72
    Events
    1.71
    Calling
    1.70
    Act Density 0.001%

    No Known Activations