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

    Neuronpedia

    INDEX
    Explanations

    discussions related to ethical concerns and implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uko
    -0.14
     LIABLE
    -0.14
    ioneer
    -0.13
    .ta
    -0.13
    loat
    -0.13
    åİļ
    -0.13
     Unsafe
    -0.13
    Ø®Ùħ
    -0.13
    á»ĩ
    -0.13
    ACHI
    -0.13
    POSITIVE LOGITS
     minor
    0.63
    minor
    0.51
     Minor
    0.48
    Minor
    0.46
     insignificant
    0.45
     trivial
    0.43
     insign
    0.36
     small
    0.35
     harmless
    0.33
     tiny
    0.32
    Act Density 0.360%

    No Known Activations