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

    Neuronpedia

    INDEX
    Explanations

    specific descriptors for individuals and their professions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abilit
    -0.15
    ána
    -0.15
    adores
    -0.15
    uti
    -0.14
    ži
    -0.14
    748
    -0.14
     Intr
    -0.14
    áte
    -0.14
     Inv
    -0.13
    fik
    -0.13
    POSITIVE LOGITS
    polit
    0.18
     politik
    0.17
     jur
    0.16
     ped
    0.16
    paint
    0.16
     politician
    0.16
     painting
    0.15
     polit
    0.15
    _paint
    0.15
     ge
    0.15
    Act Density 0.028%

    No Known Activations