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

    Neuronpedia

    INDEX
    Explanations

    mentions or variations of the name "Horace"

    oai_token-act-pair · gpt-3.5-turbo

    references to horror-related themes or content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģ¦
    -0.71
     Leilan
    -0.68
    eer
    -0.67
    ãģ®éŃĶ
    -0.66
     appraisal
    -0.60
    eers
    -0.59
     supplemental
    -0.59
     graded
    -0.58
     vigorously
    -0.57
    REDACTED
    -0.57
    POSITIVE LOGITS
    izontal
    1.63
    rible
    1.54
    izont
    1.46
    ribly
    1.44
    izons
    1.43
    rors
    1.34
    izon
    1.33
    ror
    1.30
    rified
    1.17
    oscope
    1.14
    Act Density 0.024%

    No Known Activations