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

    Neuronpedia

    INDEX
    Explanations

    elements related to ranking or assessment indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çī
    -0.17
    osy
    -0.16
    //{{
    -0.15
    _instr
    -0.15
    oda
    -0.15
    .IsAny
    -0.15
    zcze
    -0.14
     Ere
    -0.14
    owler
    -0.14
    ãĥŃ
    -0.14
    POSITIVE LOGITS
    ums
    0.16
    emory
    0.15
    rend
    0.14
     explic
    0.14
    untime
    0.14
     Hang
    0.14
     entertainment
    0.14
    cv
    0.14
    Deck
    0.14
     Deck
    0.14
    Act Density 0.019%

    No Known Activations