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

    Neuronpedia

    INDEX
    Explanations

    adverbs expressing a strong degree of intensity or certainty

    oai_token-act-pair · gpt-3.5-turbo

    intensifiers that convey strong opinions or emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.71
    arta
    -0.70
     passage
    -0.68
    arthed
    -0.63
    elsen
    -0.63
    berman
    -0.63
    rikes
    -0.62
    uli
    -0.62
    rats
    -0.62
     Provision
    -0.62
    POSITIVE LOGITS
     disple
    0.81
    BuyableInstoreAndOnline
    0.74
     confusing
    0.73
     uncomfortable
    0.71
     nostalgic
    0.71
     inaccurate
    0.70
     confused
    0.69
     difficult
    0.69
     complicated
    0.68
    interesting
    0.68
    Act Density 0.015%

    No Known Activations