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

    Neuronpedia

    INDEX
    Explanations

    words related to things that are unexpected or surprising

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "surprising."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -1.06
    xia
    -0.91
    nan
    -0.90
    tein
    -0.85
    haps
    -0.84
    iche
    -0.80
    ript
    -0.75
    adian
    -0.75
    claimer
    -0.74
    nery
    -0.73
    POSITIVE LOGITS
     Squid
    0.90
    aneously
    0.87
     surprising
    0.85
    LY
    0.83
     surprises
    0.82
     surpr
    0.79
     enough
    0.79
     coincidence
    0.78
     revelations
    0.77
    Berry
    0.77
    Act Density 0.015%

    No Known Activations