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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe existence or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rts
    -0.16
    contres
    -0.15
    xis
    -0.15
    ovit
    -0.14
    urus
    -0.14
    wiÄħz
    -0.13
     Weaver
    -0.13
     Göz
    -0.13
    patch
    -0.13
    iams
    -0.13
    POSITIVE LOGITS
    chner
    0.15
    let
    0.15
    zcze
    0.15
    EATURE
    0.14
    ÙĬز
    0.14
     Upper
    0.14
    eger
    0.13
    842
    0.13
    enty
    0.13
     whose
    0.13
    Act Density 0.199%

    No Known Activations