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

    Neuronpedia

    INDEX
    Explanations

    words that convey positive attributes or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iley
    -0.16
    DonaldTrump
    -0.15
    ').'
    -0.15
    loo
    -0.15
    วà¸Ķ
    -0.14
    audi
    -0.14
    raham
    -0.14
    rame
    -0.14
    FINITE
    -0.13
    rát
    -0.13
    POSITIVE LOGITS
     etc
    0.24
    çŃī
    0.18
    etc
    0.17
    sole
    0.16
     hatta
    0.14
    -looking
    0.14
    memberof
    0.14
    ubb
    0.14
    anio
    0.14
     subt
    0.14
    Act Density 0.075%

    No Known Activations