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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating possibility or permission

    oai_token-act-pair · gpt-3.5-turbo

    suggestions or possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oric
    -0.78
     Lauder
    -0.71
    cies
    -0.69
    ials
    -0.68
     Dragonbound
    -0.68
    rett
    -0.65
     Enforcement
    -0.63
    pires
    -0.63
    shall
    -0.62
    heid
    -0.62
    POSITIVE LOGITS
     someday
    1.02
     feas
    0.90
    haps
    0.89
     conce
    0.88
    aea
    0.85
    ily
    0.84
    nown
    0.84
    iest
    0.83
     be
    0.80
     plaus
    0.80
    Act Density 0.044%

    No Known Activations