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

    Neuronpedia

    INDEX
    Explanations

    events or changes that have occurred recently

    oai_token-act-pair · gpt-3.5-turbo

    references to recent events or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     instantaneous
    -0.70
    ibles
    -0.67
     Monstrous
    -0.63
     Conquer
    -0.62
     1908
    -0.60
    utch
    -0.58
     mixture
    -0.58
     Bones
    -0.58
     2019
    -0.57
     1904
    -0.57
    POSITIVE LOGITS
    senal
    0.87
    Reviewer
    0.83
    bernatorial
    0.83
    leases
    0.74
    LEASE
    0.73
    lished
    0.71
    comings
    0.69
    nesday
    0.69
    ulner
    0.67
    ploy
    0.65
    Act Density 0.230%

    No Known Activations