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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating references or attributions to specific concepts or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.03
    2:0.13
    3:0.07
    4:0.09
    5:0.05
    6:0.12
    7:0.17
    8:0.05
    9:0.05
    10:0.08
    11:0.08
    Negative Logits
     uniforms
    -1.59
     cabinets
    -1.56
     accompanying
    -1.45
     luggage
    -1.43
     salads
    -1.42
     appointments
    -1.40
     flyer
    -1.40
    VERTISEMENT
    -1.39
     robes
    -1.39
    ]}
    -1.36
    POSITIVE LOGITS
    ゴ
    1.83
    learn
    1.70
    ブ
    1.52
    anta
    1.49
     Questions
    1.47
    hi
    1.46
     QUEST
    1.46
    terness
    1.46
    raq
    1.42
    ouple
    1.41
    Act Density 0.000%

    No Known Activations