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

    Neuronpedia

    INDEX
    Explanations

    references to entities and their actions or statuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GOTREF
    -0.65
     myſelf
    -0.64
    withOpacity
    -0.63
    isContained
    -0.62
    ArgsConstructor
    -0.59
    MessageState
    -0.58
    extAlignment
    -0.57
    DropTable
    -0.57
     ་་
    -0.56
    WaitGroup
    -0.56
    POSITIVE LOGITS
     they
    0.71
    Pyx
    0.64
     They
    0.64
    ValueStyle
    0.62
    They
    0.62
    yorlar
    0.54
    ('*',
    0.54
     stick
    0.54
     themselves
    0.54
     referenties
    0.52
    Act Density 0.167%

    No Known Activations