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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sports events or coverage

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ime" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atform
    -0.90
    istani
    -0.86
    heses
    -0.83
    roads
    -0.82
    iege
    -0.81
    roma
    -0.79
    ivity
    -0.78
    oran
    -0.77
    sburgh
    -0.77
    amara
    -0.76
    POSITIVE LOGITS
    ographed
    0.88
    lda
    0.84
    ously
    0.77
    cki
    0.73
    lled
    0.70
    hower
    0.68
    phrine
    0.68
    lla
    0.68
    urs
    0.67
    cale
    0.62
    Act Density 0.066%

    No Known Activations