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

    Neuronpedia

    INDEX
    Explanations

    terms related to numeric data or counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    swap
    -0.16
    SDL
    -0.16
    sov
    -0.16
     風
    -0.15
    blr
    -0.14
    ÐŁÐļ
    -0.14
    öl
    -0.14
    prs
    -0.14
    _DISABLE
    -0.14
     Irving
    -0.14
    POSITIVE LOGITS
     shadow
    0.16
    uite
    0.15
    ırak
    0.14
    ddy
    0.14
    imen
    0.14
     Shadow
    0.14
     �
    0.14
    ظÙģ
    0.14
    idel
    0.13
    oral
    0.13
    Act Density 0.008%

    No Known Activations