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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating assessments or evaluations of people or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LineColor
    -0.16
     Nut
    -0.16
    аниÑĨ
    -0.15
    antt
    -0.15
    Nut
    -0.15
    ÙĪÛĮس
    -0.15
    stm
    -0.15
    cctor
    -0.15
    å´İ
    -0.15
    æ¬
    -0.14
    POSITIVE LOGITS
     Operators
    0.14
    CDF
    0.14
    reira
    0.14
    érica
    0.14
    919
    0.14
    ilin
    0.14
    109
    0.13
    ner
    0.13
    ails
    0.13
     Mend
    0.13
    Act Density 0.015%

    No Known Activations