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

    Neuronpedia

    INDEX
    Explanations

    dates or names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    names and affiliations related to individuals or groups within a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esville
    -0.91
    alg
    -0.90
    ted
    -0.87
    mates
    -0.84
    ting
    -0.83
    rament
    -0.78
    rays
    -0.77
    izoph
    -0.76
    lag
    -0.75
    riad
    -0.74
    POSITIVE LOGITS
    Ô
    0.83
    EGIN
    0.75
    ptions
    0.74
    isons
    0.74
    apons
    0.73
    isance
    0.72
    ptin
    0.71
    vernment
    0.70
    IBLE
    0.69
    sembly
    0.68
    Act Density 0.040%

    No Known Activations