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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing something likely to succeed or bring good results

    oai_token-act-pair · gpt-3.5-turbo

    terms that indicate potential or positive outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illon
    -0.84
    avia
    -0.82
    cation
    -0.82
    FactoryReloaded
    -0.76
    cise
    -0.75
    aida
    -0.75
    cest
    -0.73
    ento
    -0.71
    dain
    -0.70
    nery
    -0.70
    POSITIVE LOGITS
     prospects
    0.97
    ly
    0.97
     promising
    0.87
    NESS
    0.79
    LY
    0.73
    ness
    0.72
     cannabin
    0.71
     newcomer
    0.68
    fully
    0.68
     youngster
    0.68
    Act Density 0.017%

    No Known Activations