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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    words related to identification or classification of individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ow
    -0.72
    natureconservancy
    -0.70
     Gauntlet
    -0.69
     808
    -0.69
     treadmill
    -0.68
     typew
    -0.67
     TABLE
    -0.66
     Wat
    -0.65
     knob
    -0.65
    socket
    -0.65
    POSITIVE LOGITS
    an
    1.55
    AN
    1.41
    ans
    1.34
    ano
    1.27
    ani
    1.21
    anic
    1.20
    anism
    1.19
    anian
    1.17
    ane
    1.17
    acan
    1.17
    Act Density 0.179%

    No Known Activations