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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "only" is used with a numeric value

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "only."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    insula
    -0.87
    sed
    -0.65
    multipl
    -0.63
     heterogeneity
    -0.62
    Nev
    -0.61
    hement
    -0.60
    leaders
    -0.59
    dict
    -0.59
    idon
    -0.58
     mantle
    -0.57
    POSITIVE LOGITS
     marginally
    1.08
     scratched
    0.80
     mildly
    0.77
     kidding
    0.76
     limited
    0.76
    £ı
    0.72
     allowed
    0.72
     partially
    0.71
     slightly
    0.71
     incidentally
    0.70
    Act Density 0.063%

    No Known Activations