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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences starting with "Apparently"

    oai_token-act-pair · gpt-3.5-turbo

    the word "apparently"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ching
    -0.65
    osc
    -0.64
     funeral
    -0.63
    ça
    -0.62
    rouse
    -0.61
    heat
    -0.61
     boulder
    -0.60
    iling
    -0.60
    atl
    -0.60
    andering
    -0.58
    POSITIVE LOGITS
    ãĥ¼ãĥĨãĤ£
    0.75
    Apparently
    0.72
    imaru
    0.71
    Buyable
    0.70
    endment
    0.69
     unsurprisingly
    0.68
     Apparently
    0.67
     Sigma
    0.67
    ãĤ´ãĥ³
    0.66
     inconsistency
    0.63
    Act Density 0.008%

    No Known Activations