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

    Neuronpedia

    INDEX
    Explanations

    interjections expressing surprise or disbelief

    oai_token-act-pair · gpt-3.5-turbo

    expressions of surprise or realizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IUM
    -0.82
     Construct
    -0.70
    -+-+
    -0.70
    */(
    -0.70
    IAL
    -0.68
    eers
    -0.68
    ãĤ¼ãĤ¦ãĤ¹
    -0.66
     fullest
    -0.65
    ":[{"
    -0.64
     Awakens
    -0.63
    POSITIVE LOGITS
    hhhh
    0.95
    hh
    0.93
    oho
    0.92
    umph
    0.90
    oh
    0.90
    anian
    0.86
    warts
    0.84
    hhh
    0.83
    oy
    0.82
    awk
    0.81
    Act Density 0.012%

    No Known Activations