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

    Neuronpedia

    INDEX
    Explanations

    expressions related to comparisons, often emphasizing the significant or extreme nature of a situation or action

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a comparative reduction or negation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.66
    Net
    -0.66
    unic
    -0.65
     Kau
    -0.63
    Ö¼
    -0.62
    imov
    -0.62
     Morrow
    -0.62
    Sky
    -0.62
    okin
    -0.61
    ULT
    -0.61
    POSITIVE LOGITS
     than
    0.81
    natureconservancy
    0.76
    nces
    0.75
     eloqu
    0.74
     honored
    0.70
    aneously
    0.67
     honoured
    0.67
     forgiving
    0.67
     tast
    0.66
     generous
    0.64
    Act Density 0.015%

    No Known Activations