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

    Neuronpedia

    INDEX
    Explanations

    phrases or elements that represent significant data or references in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enti
    -0.15
    azzi
    -0.15
     tube
    -0.14
    rowser
    -0.14
    porte
    -0.14
    enschaft
    -0.14
     Invent
    -0.14
    άνι
    -0.13
    261
    -0.13
    wiki
    -0.13
    POSITIVE LOGITS
     åĬ
    0.15
    è«
    0.15
     Snape
    0.15
    ey
    0.14
    kur
    0.14
    ubby
    0.14
    æľĭ
    0.14
     Levine
    0.14
    agh
    0.14
    shr
    0.13
    Act Density 0.009%

    No Known Activations