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

    Neuronpedia

    INDEX
    Explanations

    references to different versions of items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ermo
    -0.16
    -ng
    -0.15
    eron
    -0.14
    oÅĪ
    -0.14
    orie
    -0.14
    opper
    -0.14
    weed
    -0.14
    ocaly
    -0.13
    avin
    -0.13
    ress
    -0.13
    POSITIVE LOGITS
    aleigh
    0.18
     versions
    0.17
    bac
    0.16
     version
    0.16
    nage
    0.16
    versions
    0.15
    935
    0.15
    naires
    0.15
    batim
    0.15
    TY
    0.15
    Act Density 0.025%

    No Known Activations