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

    Neuronpedia

    INDEX
    Explanations

    affirmative or descriptive phrases about individuals' roles or statuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oyer
    -0.17
    istine
    -0.14
    ovice
    -0.14
    vn
    -0.14
    Unnamed
    -0.14
    aper
    -0.14
    APER
    -0.13
    ÙĪرÙĩ
    -0.13
    áº
    -0.13
    armor
    -0.13
    POSITIVE LOGITS
     among
    0.18
     professor
    0.17
     both
    0.15
     een
    0.15
     Professor
    0.14
     owner
    0.14
     our
    0.14
    eous
    0.14
     nothing
    0.14
     a
    0.14
    Act Density 0.060%

    No Known Activations