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

    Neuronpedia

    INDEX
    Explanations

    words related to erasing or removing something

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of error or mistakes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.70
     Spears
    -0.69
    ership
    -0.68
    ertodd
    -0.66
    Premium
    -0.65
     Painter
    -0.63
    hyde
    -0.63
    pring
    -0.62
    SHIP
    -0.62
    hips
    -0.62
    POSITIVE LOGITS
    asure
    1.22
    asures
    1.07
    icit
    1.02
    aser
    0.97
    asing
    0.90
    rant
    0.88
    ogenous
    0.88
    bers
    0.85
    got
    0.83
    rors
    0.82
    Act Density 0.009%

    No Known Activations