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

    Neuronpedia

    INDEX
    Explanations

    visual markers or symbols that may represent significant emotional states or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gian
    -0.73
    lish
    -0.68
    aria
    -0.62
    ulous
    -0.62
    hai
    -0.61
    bery
    -0.61
    gem
    -0.58
    rians
    -0.58
    irming
    -0.58
    rington
    -0.57
    POSITIVE LOGITS
     Appears
    0.62
    inker
    0.62
    urat
    0.61
     Span
    0.61
    Reviewer
    0.60
    phabet
    0.60
     hereafter
    0.57
     Ambro
    0.57
    Bern
    0.56
    After
    0.56
    Act Density 0.243%

    No Known Activations