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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal proceedings and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    teg
    -0.19
    ntl
    -0.17
    ATAL
    -0.15
    olib
    -0.15
    ODB
    -0.14
     Malk
    -0.14
    клад
    -0.14
    UTO
    -0.14
    AVE
    -0.14
    LEMENT
    -0.14
    POSITIVE LOGITS
    cannot
    0.19
     cannot
    0.19
     Cannot
    0.19
     already
    0.17
    Cannot
    0.17
    caa
    0.17
    _ALREADY
    0.16
    already
    0.15
    oret
    0.15
    CAA
    0.15
    Act Density 0.007%

    No Known Activations