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

    Neuronpedia

    INDEX
    Explanations

    words related to physical locations

    oai_token-act-pair · gpt-3.5-turbo

    words related to time and duration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atform
    -0.88
    iege
    -0.81
    hips
    -0.77
    rams
    -0.70
    raphic
    -0.68
    s
    -0.68
    ram
    -0.67
    ohn
    -0.67
    oran
    -0.67
    obal
    -0.66
    POSITIVE LOGITS
    lda
    0.91
    lled
    0.91
    arthed
    0.88
    ographed
    0.88
    lla
    0.87
    cki
    0.86
    urs
    0.82
    ño
    0.78
    phrine
    0.77
    hower
    0.77
    Act Density 0.066%

    No Known Activations