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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize personal opinions or assessments about situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reportedly
    -0.20
     ведÑĮ
    -0.17
    rians
    -0.16
    ories
    -0.15
     seemingly
    -0.15
    oldemort
    -0.15
    occo
    -0.15
     hereby
    -0.15
    ulaire
    -0.15
    izzo
    -0.14
    POSITIVE LOGITS
     fairly
    0.18
     fair
    0.16
    ucha
    0.16
    fair
    0.16
     pretty
    0.16
    ny
    0.15
     Hast
    0.15
    asa
    0.15
    o
    0.15
    hon
    0.15
    Act Density 0.271%

    No Known Activations