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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating necessity and obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /documentation
    -0.16
    otu
    -0.15
    ori
    -0.15
    apl
    -0.14
    achs
    -0.14
     دÙĪب
    -0.14
    488
    -0.14
    anon
    -0.14
    /doc
    -0.13
    _iff
    -0.13
    POSITIVE LOGITS
    dit
    0.18
    ysz
    0.16
    WISE
    0.15
    CKET
    0.15
    ì±Ħ
    0.15
    ient
    0.15
    ÑĥÑĢг
    0.14
    olib
    0.14
    bol
    0.14
    ighbor
    0.14
    Act Density 0.237%

    No Known Activations