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

    Neuronpedia

    INDEX
    Explanations

    phrases related to performing actions or tasks

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "perform" and its variants, indicating actions or duties being carried out

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osponsors
    -0.79
     Survivors
    -0.73
    resses
    -0.68
    ressed
    -0.65
     settled
    -0.63
     Sett
    -0.63
     Tooth
    -0.62
     mates
    -0.59
     wanting
    -0.59
     cans
    -0.59
    POSITIVE LOGITS
     utmost
    0.80
     diligence
    0.79
     abl
    0.75
     blockade
    0.73
    auntlet
    0.73
     coup
    0.72
     captcha
    0.72
     duties
    0.71
    issance
    0.71
    ãĥĨ
    0.71
    Act Density 0.212%

    No Known Activations