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

    Neuronpedia

    INDEX
    Explanations

    the word "Horace" with varying levels of activation

    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
    ħĭ
    -0.76
    ãģ¦
    -0.76
    anwhile
    -0.72
    ãģ®éŃĶ
    -0.71
    0000000000000000
    -0.67
     succeeding
    -0.66
     Leilan
    -0.65
    enhagen
    -0.64
     graded
    -0.62
    conservancy
    -0.61
    POSITIVE LOGITS
    izontal
    1.43
    izont
    1.38
    izons
    1.27
    rible
    1.27
    ror
    1.15
    ribly
    1.14
    izon
    1.13
    rors
    1.09
    cru
    1.08
    oscope
    1.06
    Act Density 0.026%

    No Known Activations