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

    Neuronpedia

    INDEX
    Explanations

    phrases related to batches or groups of items

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "of."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     foresee
    -0.74
    ibe
    -0.69
    irs
    -0.66
    ashtra
    -0.63
     estimating
    -0.62
    acus
    -0.62
    ļéĨĴ
    -0.61
     Kimber
    -0.60
     whisper
    -0.60
    antics
    -0.60
    POSITIVE LOGITS
     sorts
    0.87
    icial
    0.73
    icles
    0.70
    icle
    0.67
    akeru
    0.66
    milo
    0.59
    esome
    0.59
     course
    0.59
     entries
    0.58
    ilan
    0.57
    Act Density 0.406%

    No Known Activations