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

    Neuronpedia

    INDEX
    Explanations

    locations or unspecified places

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "anywhere" indicating varied locations or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apo
    -0.75
    asting
    -0.72
    bal
    -0.72
    seless
    -0.68
    asts
    -0.68
    roma
    -0.67
    ulously
    -0.66
    othy
    -0.66
    pu
    -0.66
    quel
    -0.65
    POSITIVE LOGITS
     else
    1.43
    abouts
    1.17
    Else
    1.13
     Else
    1.12
     imaginable
    0.94
    else
    0.90
    where
    0.82
    ĪĴ
    0.76
    ħĭ
    0.75
     conceivable
    0.71
    Act Density 0.015%

    No Known Activations