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

    Neuronpedia

    INDEX
    Explanations

    articles with a special character blending in

    oai_token-act-pair · gpt-3.5-turbo

    references to statistical data or measurements related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prosec
    -0.85
     aven
    -0.80
     neighb
    -0.75
     undecided
    -0.74
     pard
    -0.74
     tornado
    -0.73
     rebell
    -0.73
     crumble
    -0.71
     unsolved
    -0.71
     pudding
    -0.70
    POSITIVE LOGITS
    SPONSORED
    1.90
    Specifically
    1.80
    According
    1.75
    Among
    1.75
    Each
    1.68
    Initially
    1.66
    Using
    1.65
    The
    1.65
    Unlike
    1.65
    Its
    1.63
    Act Density 0.378%

    No Known Activations