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

    Neuronpedia

    INDEX
    Explanations

    references to specific body parts, particularly fingers

    oai_token-act-pair · gpt-3.5-turbo

    references to fingers and their usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DEF
    -0.75
     Constantin
    -0.73
    nce
    -0.70
     [|
    -0.69
    Sov
    -0.69
    nom
    -0.66
     Vide
    -0.66
    nance
    -0.65
    ¥µ
    -0.65
    URRENT
    -0.63
    POSITIVE LOGITS
     fingers
    1.22
    pring
    1.02
    ingers
    0.97
     paws
    0.94
     finger
    0.92
     thumb
    0.91
    mith
    0.89
    aws
    0.88
     nails
    0.87
    maid
    0.86
    Act Density 0.012%

    No Known Activations