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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the suffix "ker" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UME
    -0.75
     Cind
    -0.69
     historic
    -0.65
     gulf
    -0.61
     stringent
    -0.60
    GoldMagikarp
    -0.60
     tense
    -0.59
    ERROR
    -0.58
     Orwell
    -0.58
    UE
    -0.58
    POSITIVE LOGITS
    ker
    1.22
    chief
    1.09
    kers
    0.92
    lund
    0.92
    luster
    0.90
    holm
    0.86
    icker
    0.86
    pedia
    0.85
    king
    0.85
    rigan
    0.83
    Act Density 0.007%

    No Known Activations