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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "good" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.17
    aldo
    -0.15
    å¼ı
    -0.15
    /OR
    -0.15
    oretical
    -0.15
    xic
    -0.15
    orative
    -0.15
    oot
    -0.14
    adu
    -0.14
    ADER
    -0.14
    POSITIVE LOGITS
    reads
    0.19
    liest
    0.19
     enough
    0.17
    bye
    0.17
    acre
    0.17
    owler
    0.16
     Enough
    0.16
    -quality
    0.15
     migrationBuilder
    0.15
    rich
    0.15
    Act Density 0.090%

    No Known Activations