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

    Neuronpedia

    INDEX
    Explanations

    mentions of the body part "fingers"

    oai_token-act-pair · gpt-3.5-turbo

    references to fingers and thumbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     [|
    -0.78
    judicial
    -0.70
    house
    -0.69
     Det
    -0.68
    nz
    -0.67
    public
    -0.66
    houses
    -0.66
     Constantin
    -0.65
    nce
    -0.65
    spect
    -0.64
    POSITIVE LOGITS
     fingers
    1.19
    ingers
    1.14
    pring
    1.12
    mith
    0.99
    aws
    0.98
    creen
    0.97
    leeve
    0.91
     thumb
    0.89
    hops
    0.88
     paws
    0.84
    Act Density 0.010%

    No Known Activations