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

    Neuronpedia

    INDEX
    Explanations

    comparisons of quantity or degree

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating increasing amounts or frequencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ©
    -0.69
    borg
    -0.68
    OCK
    -0.67
    ����
    -0.66
     Classification
    -0.65
    ãĥĥãĤ¯
    -0.64
    xtap
    -0.63
    ãĤ«
    -0.62
    ãĥĵ
    -0.62
    boxing
    -0.61
    POSITIVE LOGITS
     than
    0.85
    hest
    0.83
     realistic
    0.79
     adventurous
    0.78
     affluent
    0.76
     plausible
    0.75
    achy
    0.75
     prevalent
    0.74
     desirable
    0.74
     complicated
    0.73
    Act Density 0.020%

    No Known Activations