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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the name "Horace."

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Horace."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.83
    ãģ¦
    -0.79
    0000000000000000
    -0.78
    ãģ®éŃĶ
    -0.70
     succeeding
    -0.67
    enhagen
    -0.67
    BOOK
    -0.66
     graded
    -0.65
    eer
    -0.65
     Bakr
    -0.62
    POSITIVE LOGITS
    izont
    1.36
    izontal
    1.31
    izons
    1.17
    rible
    1.07
    oscope
    1.05
    ribly
    0.98
    izon
    0.96
    rors
    0.92
    rigan
    0.92
    ror
    0.92
    Act Density 0.017%

    No Known Activations