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

    Neuronpedia

    INDEX
    Explanations

    contractions and possessive forms

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to emotional states or actions of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oner
    -0.64
     Composite
    -0.64
     Examination
    -0.64
     Classification
    -0.63
    omsky
    -0.62
     Denis
    -0.61
    vision
    -0.60
     Nanto
    -0.60
    detail
    -0.59
    lear
    -0.59
    POSITIVE LOGITS
     inevitably
    0.72
     mattered
    0.72
     idle
    0.71
     inconvenient
    0.68
     peril
    0.68
     shine
    0.67
     darkest
    0.67
     hottest
    0.66
     malf
    0.66
    wcsstore
    0.66
    Act Density 0.271%

    No Known Activations