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

    Neuronpedia

    INDEX
    Explanations

    names of individuals, particularly focusing on the name "Herman."

    oai_token-act-pair · gpt-3.5-turbo

    the name "Herman" mentioned in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acular
    -0.83
    REAM
    -0.76
    akening
    -0.76
    alam
    -0.73
    ertodd
    -0.71
    ODUCT
    -0.69
    avis
    -0.69
    Constructed
    -0.68
    ulhu
    -0.67
    ridges
    -0.67
    POSITIVE LOGITS
    nian
    0.94
     Cain
    0.93
    stein
    0.90
    wald
    0.90
    n
    0.88
    mann
    0.86
    stal
    0.82
    thal
    0.79
    tz
    0.79
    ns
    0.79
    Act Density 0.048%

    No Known Activations