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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to establishing precedents or setting the tone for future actions or events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to setting standards, precedents, or foundations for various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    den
    -0.68
     abolished
    -0.67
     contracted
    -0.66
    oked
    -0.63
     suppressed
    -0.62
    die
    -0.62
    hent
    -0.62
    umb
    -0.61
    loving
    -0.61
    tan
    -0.60
    POSITIVE LOGITS
    FontSize
    0.95
    Enlarge
    0.81
    çīĪ
    0.73
    ISION
    0.72
    TPS
    0.70
     LEVEL
    0.69
    oise
    0.68
    LEASE
    0.67
    Engineers
    0.67
    enium
    0.66
    Act Density 0.134%

    No Known Activations