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

    Neuronpedia

    INDEX
    Explanations

    words related to exclusivity and limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    porte
    -0.16
    mnop
    -0.15
    LOCKS
    -0.15
    ivet
    -0.15
    leh
    -0.14
     gyr
    -0.14
    hots
    -0.14
    progressbar
    -0.14
     çIJ
    -0.14
    ighton
    -0.14
    POSITIVE LOGITS
    cond
    0.16
    ød
    0.15
     outr
    0.15
    umann
    0.14
    rick
    0.14
     void
    0.14
    829
    0.14
    .lists
    0.14
    undos
    0.14
    ursday
    0.14
    Act Density 0.004%

    No Known Activations