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

    Neuronpedia

    INDEX
    Explanations

    proper names

    oai_token-act-pair · gpt-3.5-turbo

    names and references associated with individuals, particularly those related to sports and entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    groups
    -0.75
    hov
    -0.72
    PASS
    -0.68
    writers
    -0.65
    xus
    -0.64
    ebted
    -0.63
    duino
    -0.62
    cffffcc
    -0.61
    exempt
    -0.60
     spect
    -0.60
    POSITIVE LOGITS
    ruary
    0.99
    hower
    0.75
     Akin
    0.71
    illet
    0.68
    uca
    0.66
    rique
    0.66
    avier
    0.65
    glas
    0.64
    abase
    0.63
    acci
    0.62
    Act Density 0.218%

    No Known Activations