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

    Neuronpedia

    INDEX
    Explanations

    words related to a specific name "Gero" with varying levels of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "hero."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ń·
    -0.80
     Fif
    -0.71
    hips
    -0.69
    liam
    -0.66
    lv
    -0.65
    orney
    -0.65
     Beaver
    -0.63
     Freed
    -0.62
     Siber
    -0.60
    olulu
    -0.59
    POSITIVE LOGITS
    ero
    1.41
    edia
    1.08
    osa
    0.83
    eli
    0.80
    ose
    0.79
    STAR
    0.79
    oma
    0.79
    oses
    0.78
    ophon
    0.77
    quin
    0.76
    Act Density 0.005%

    No Known Activations