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

    Neuronpedia

    INDEX
    Explanations

    phrases or isolations within double quotes

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and transitional phrases related to conflict and resolution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Saiyan
    -0.63
    pie
    -0.63
     Stard
    -0.62
    akedown
    -0.60
    ½
    -0.59
    opolis
    -0.58
     concludes
    -0.57
    Ĭ
    -0.56
     Quit
    -0.56
     harass
    -0.56
    POSITIVE LOGITS
    Introduced
    0.94
    According
    0.85
    During
    0.85
    Statistics
    0.84
    Since
    0.82
    Unlike
    0.79
    Writing
    0.79
    Among
    0.79
    ccording
    0.79
    Although
    0.79
    Act Density 0.297%

    No Known Activations