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

    Neuronpedia

    INDEX
    Explanations

    quantifiable statistics and measurements related to safety or health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .rpm
    -0.15
    iband
    -0.14
    çĶŁçļĦ
    -0.14
    032
    -0.14
    uelles
    -0.14
    زد
    -0.13
    _$_
    -0.13
    CodeGen
    -0.13
    byt
    -0.13
    ä¸ŃåѦ
    -0.13
    POSITIVE LOGITS
    100
    0.16
    oulos
    0.15
    ove
    0.14
    ault
    0.14
     square
    0.14
    ql
    0.14
    -pop
    0.14
    aras
    0.14
     unit
    0.13
    363
    0.13
    Act Density 0.043%

    No Known Activations