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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing comparison or contrast

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating mental states or cognitive processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antry
    -0.66
    aily
    -0.64
    chenko
    -0.63
    also
    -0.62
    jri
    -0.60
    azer
    -0.60
    sonian
    -0.60
    lov
    -0.59
    dh
    -0.59
    opian
    -0.58
    POSITIVE LOGITS
    ¼
    0.66
    Sphere
    0.64
     <=
    0.64
     Colossus
    0.62
    elected
    0.60
    ©¶æ
    0.59
     societies
    0.59
     SOME
    0.57
    handed
    0.57
    esta
    0.57
    Act Density 0.317%

    No Known Activations