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

    Neuronpedia

    INDEX
    Explanations

    sentences related to progress or improvement

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a desire for improvement or progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     forbids
    -0.78
    anwhile
    -0.71
     notwithstanding
    -0.68
     notably
    -0.67
     teaches
    -0.67
     Appears
    -0.65
     reportedly
    -0.64
     moreover
    -0.64
     unsurprisingly
    -0.64
     furthermore
    -0.63
    POSITIVE LOGITS
    agra
    0.71
     proverbial
    0.70
    poke
    0.66
    agine
    0.65
    morrow
    0.64
    umbn
    0.63
    Sov
    0.63
     barg
    0.63
    ctrl
    0.62
    pressed
    0.61
    Act Density 4.434%

    No Known Activations