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

    Neuronpedia

    INDEX
    Explanations

    names of individuals, particularly those with initials

    oai_token-act-pair · gpt-3.5-turbo

    references to prominent individuals, particularly those named Robert

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    warm
    -0.72
    etheless
    -0.68
    yip
    -0.66
     Nadu
    -0.63
    javascript
    -0.63
    pour
    -0.62
    ibo
    -0.61
     Pixie
    -0.61
    akeru
    -0.60
    046
    -0.60
    POSITIVE LOGITS
    ¶æ
    0.72
    ij士
    0.70
    eston
    0.70
    lund
    0.66
    ħĭ
    0.66
     Wilhelm
    0.65
    anson
    0.63
    ector
    0.63
    Ľ
    0.63
     Curve
    0.62
    Act Density 0.141%

    No Known Activations