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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    the name "Kiel" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hedral
    -0.78
    ricular
    -0.77
    rament
    -0.65
     DRAGON
    -0.60
    urnal
    -0.59
    ©¶æ¥µ
    -0.58
    rophic
    -0.58
    natureconservancy
    -0.57
    picking
    -0.57
    hered
    -0.57
    POSITIVE LOGITS
    ibrary
    1.10
    anguage
    0.94
    stadt
    0.93
    ounge
    0.92
    ocene
    0.84
    er
    0.84
    abel
    0.83
    iberal
    0.82
    mann
    0.81
    ands
    0.81
    Act Density 0.034%

    No Known Activations