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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks that signal pauses or breaks in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.76
    ecd
    -0.74
    ensional
    -0.69
    redients
    -0.69
    enhagen
    -0.67
     artif
    -0.67
    ionage
    -0.66
    catentry
    -0.65
     wip
    -0.65
    forced
    -0.63
    POSITIVE LOGITS
     Rowling
    0.89
    oval
    0.79
     Chest
    0.78
    ulu
    0.76
    ucha
    0.69
     Lumpur
    0.69
    Row
    0.69
    hiro
    0.69
    EStreamFrame
    0.68
    atri
    0.68
    Act Density 0.010%

    No Known Activations