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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing consequences or relationships between actions and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egas
    -0.17
    ventus
    -0.16
    iverz
    -0.15
    indr
    -0.15
    ocks
    -0.15
    cko
    -0.15
    oose
    -0.14
    cf
    -0.14
    orno
    -0.14
    hardt
    -0.14
    POSITIVE LOGITS
    ises
    0.15
    .sy
    0.15
     Genius
    0.15
    rzy
    0.14
    oll
    0.14
    .Zip
    0.13
    _CTL
    0.13
     FileUtils
    0.13
     moi
    0.13
     tú
    0.13
    Act Density 0.091%

    No Known Activations