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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating origin or movement

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the origin or source of individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    faced
    -0.88
    washer
    -0.76
    busters
    -0.75
    ographs
    -0.74
    quote
    -0.74
    sticks
    -0.73
    tops
    -0.72
    proven
    -0.69
    Matrix
    -0.68
    ometers
    -0.68
    POSITIVE LOGITS
     afar
    1.29
     abroad
    1.02
     whom
    0.98
     Brune
    0.91
     Denmark
    0.78
     whence
    0.78
     across
    0.78
     Ethiopia
    0.78
     Uganda
    0.76
     Alexandria
    0.76
    Act Density 0.100%

    No Known Activations