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

    Neuronpedia

    INDEX
    Explanations

    words related to specific geographic locations or directions within a place

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating geographical divisions or sections of places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ullivan
    -0.66
    icer
    -0.61
    ÃįÃį
    -0.60
    NG
    -0.59
    umsy
    -0.59
     Parenthood
    -0.58
    aternal
    -0.58
    pload
    -0.57
    isen
    -0.57
    escription
    -0.55
    POSITIVE LOGITS
     of
    1.33
     thereof
    1.20
     Of
    0.93
    of
    0.93
     OF
    0.87
    Of
    0.87
     outskirts
    0.75
     corner
    0.75
    OF
    0.74
    oft
    0.72
    Act Density 0.186%

    No Known Activations