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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names starting with "Tr"

    oai_token-act-pair · gpt-3.5-turbo

    names of places or entities, especially those related to locations and affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     innocence
    -0.64
     seiz
    -0.62
    romeda
    -0.61
    âĢ¢âĢ¢
    -0.61
     sunset
    -0.61
    erest
    -0.61
     Archdemon
    -0.60
     prosper
    -0.59
     mortar
    -0.58
    Reloaded
    -0.58
    POSITIVE LOGITS
    quist
    0.82
    lycer
    0.78
    ħĭ
    0.77
    itte
    0.76
    portation
    0.76
    usted
    0.72
    oving
    0.70
    azo
    0.70
    edes
    0.69
    opers
    0.69
    Act Density 0.091%

    No Known Activations