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

    Neuronpedia

    INDEX
    Explanations

    terms associated with catastrophic events or severe impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erva
    -0.17
    ething
    -0.16
    ersh
    -0.16
    owa
    -0.15
    onavir
    -0.15
    agan
    -0.14
    xAC
    -0.14
    iffin
    -0.14
    caff
    -0.14
    ENTA
    -0.14
    POSITIVE LOGITS
    itto
    0.15
     Bard
    0.15
    ged
    0.14
    SSI
    0.14
    ablish
    0.14
    reed
    0.14
    .wordpress
    0.14
     Gregory
    0.14
    @a
    0.14
    locked
    0.13
    Act Density 0.007%

    No Known Activations