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

    Neuronpedia

    INDEX
    Explanations

    references to different types of soap and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lias
    -0.16
     stabil
    -0.15
    INU
    -0.15
    azzi
    -0.14
    igham
    -0.14
    ulus
    -0.14
    appa
    -0.14
    ond
    -0.14
    tings
    -0.14
    tees
    -0.13
    POSITIVE LOGITS
    ackbar
    0.15
     Gordon
    0.14
    519
    0.14
    orre
    0.14
    _THROW
    0.14
    hower
    0.14
     createAction
    0.13
     Kosten
    0.13
     Brit
    0.13
    NS
    0.13
    Act Density 0.034%

    No Known Activations