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

    Neuronpedia

    INDEX
    Explanations

    phrases that include film titles and associated characters or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibi
    -0.16
    HITE
    -0.16
    pollo
    -0.15
    letic
    -0.15
     seins
    -0.15
    unma
    -0.15
    _pdata
    -0.15
    orks
    -0.14
    FromClass
    -0.14
    owie
    -0.14
    POSITIVE LOGITS
    atos
    0.16
     Mr
    0.15
    anc
    0.14
    ario
    0.14
     Voll
    0.14
    Mr
    0.14
     slopes
    0.14
    mb
    0.13
    bus
    0.13
     weekdays
    0.13
    Act Density 0.063%

    No Known Activations