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

    Neuronpedia

    INDEX
    Explanations

    terms related to nominations and awards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fully
    -0.20
    zeug
    -0.16
    pery
    -0.14
    htm
    -0.14
    alar
    -0.14
    umin
    -0.14
     Templ
    -0.14
     knowledge
    -0.14
    amburger
    -0.14
    arian
    -0.14
    POSITIVE LOGITS
    ILED
    0.18
    omial
    0.17
    ç¿°
    0.16
    ESCO
    0.15
    warts
    0.15
    iled
    0.15
    lád
    0.15
    زد
    0.14
    ignet
    0.14
    astle
    0.14
    Act Density 0.014%

    No Known Activations