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

    Neuronpedia

    INDEX
    Explanations

    terms related to accusations and syllables

    oai_token-act-pair · gpt-3.5-turbo

    mentions of accusations and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Grant
    -0.93
    render
    -0.75
    Hug
    -0.74
     Grant
    -0.71
    LY
    -0.68
    FactoryReloaded
    -0.67
    IELD
    -0.66
    Donnell
    -0.66
     Protector
    -0.66
     Higgins
    -0.65
    POSITIVE LOGITS
    atory
    0.99
    iaries
    0.97
    ers
    0.94
    atable
    0.91
    estones
    0.84
    atorial
    0.82
    itely
    0.82
    ential
    0.80
    ateur
    0.78
    ļ
    0.78
    Act Density 0.023%

    No Known Activations