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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing judgment or condemnation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idal
    -0.22
     mortal
    -0.19
    ooke
    -0.15
    asca
    -0.14
    ided
    -0.14
    oler
    -0.14
    apid
    -0.14
    igid
    -0.14
    mong
    -0.14
     onBind
    -0.14
    POSITIVE LOGITS
     Ending
    0.16
     UNU
    0.15
    ['__
    0.14
    _OPTS
    0.14
    bow
    0.13
    λεκ
    0.13
    /sweetalert
    0.13
    oglobin
    0.13
     lé
    0.13
    rowsable
    0.13
    Act Density 0.127%

    No Known Activations