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

    Neuronpedia

    INDEX
    Explanations

    adverbs that intensify the action being described

    oai_token-act-pair · gpt-3.5-turbo

    adverbs and qualifications that emphasize effort and intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pherd
    -0.72
     Registry
    -0.66
     towed
    -0.64
    hler
    -0.64
    NING
    -0.64
     Register
    -0.61
     Ruler
    -0.60
    veyard
    -0.60
     architects
    -0.60
     Restaurant
    -0.58
    POSITIVE LOGITS
    thin
    0.81
    technical
    0.72
    direct
    0.71
    different
    0.70
    eros
    0.68
    \/\/
    0.67
     differently
    0.67
    grades
    0.66
    apons
    0.65
    CTV
    0.65
    Act Density 0.403%

    No Known Activations