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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating inclusivity or diversity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancode
    -0.17
    ncia
    -0.15
    tach
    -0.15
    loom
    -0.14
    .lesson
    -0.14
    ax
    -0.14
    mani
    -0.13
    aneously
    -0.13
    abilit
    -0.13
    ripper
    -0.13
    POSITIVE LOGITS
     sami
    0.16
     Mattis
    0.15
     cấp
    0.14
    sortable
    0.13
    iya
    0.13
    843
    0.13
     Mixed
    0.13
    دث
    0.13
    ette
    0.13
    enburg
    0.13
    Act Density 0.070%

    No Known Activations