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

    Neuronpedia

    INDEX
    Explanations

    contractions and possessive forms

    oai_token-act-pair · gpt-3.5-turbo

    special characters or typographical anomalies in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipel
    -0.86
    assetsadobe
    -0.75
    arov
    -0.72
    ogical
    -0.72
    igious
    -0.72
    ogl
    -0.70
    è¦ļéĨĴ
    -0.68
    agos
    -0.68
    odium
    -0.67
    owan
    -0.66
    POSITIVE LOGITS
    \\\\\\\\\\\\\\\\
    0.79
    ve
    0.74
    âĤ¬
    0.72
    ll
    0.71
    VE
    0.71
     ll
    0.70
    s
    0.69
    ses
    0.67
    thens
    0.67
    meric
    0.66
    Act Density 0.076%

    No Known Activations