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

    Neuronpedia

    INDEX
    Explanations

    adjectives that describe levels of quality or effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PU
    -0.16
    loff
    -0.15
    rzy
    -0.15
    nothrow
    -0.14
     peng
    -0.14
     Nz
    -0.14
    orias
    -0.14
    ãĥ¼ãĤ¯
    -0.13
    apor
    -0.13
    atern
    -0.13
    POSITIVE LOGITS
    ิà¸Ĭ
    0.17
    ;y
    0.15
    sat
    0.15
    .Apis
    0.14
    .sat
    0.14
    ê³
    0.14
     Horton
    0.14
    ÙĪØŃ
    0.14
    ly
    0.14
     understanding
    0.14
    Act Density 0.129%

    No Known Activations