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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate support, promotion, and improvement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uyá»ĩt
    -0.15
    ses
    -0.15
    edException
    -0.15
    lox
    -0.14
    urses
    -0.14
     Programmer
    -0.14
    æ£ĭçīĮ
    -0.14
    (dw
    -0.14
     Hairst
    -0.13
    едак
    -0.13
    POSITIVE LOGITS
    berger
    0.16
     pur
    0.15
    addin
    0.14
     Wellington
    0.14
     Bonds
    0.14
    nants
    0.14
    Specification
    0.14
    idis
    0.14
     notice
    0.13
    lap
    0.13
    Act Density 0.711%

    No Known Activations