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

    Neuronpedia

    INDEX
    Explanations

    adjectives or past participles with a specific ending

    oai_token-act-pair · gpt-3.5-turbo

    words related to skepticism, triviality, and struggle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mosqu
    -0.78
    Þ
    -0.77
     eleph
    -0.68
     tremend
    -0.65
     satell
    -0.65
     tyr
    -0.62
     endorsements
    -0.61
    senal
    -0.60
     participation
    -0.60
     verbs
    -0.59
    POSITIVE LOGITS
    ioned
    1.01
    ighed
    0.99
    ially
    0.92
    icked
    0.91
    ledged
    0.89
    anced
    0.85
    itely
    0.84
    hed
    0.82
    inged
    0.82
    kered
    0.82
    Act Density 0.163%

    No Known Activations