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

    Neuronpedia

    INDEX
    Explanations

    negative and critical language related to films, stories, or personal assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    íĴĪ
    -0.14
     gad
    -0.14
    ANO
    -0.14
    _mgmt
    -0.14
     permanent
    -0.13
    éri
    -0.13
    manent
    -0.13
    FORMAT
    -0.13
    Ã
    -0.13
    ìŀij
    -0.13
    POSITIVE LOGITS
    aru
    0.15
    маз
    0.15
    olley
    0.15
    agas
    0.14
    atars
    0.14
     ç¿
    0.14
     Algorithms
    0.13
    -REAL
    0.13
    leich
    0.13
    ãĤ¢ãĥ«
    0.13
    Act Density 0.048%

    No Known Activations