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

    Neuronpedia

    INDEX
    Explanations

    instances of saying "no" or refusal in conversation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phin
    -0.15
    ophage
    -0.14
    casecmp
    -0.14
    ายà¸Ļ
    -0.14
     adı
    -0.14
    isFunction
    -0.14
    instein
    -0.14
    Ñīий
    -0.14
    еÑĤа
    -0.14
    rell
    -0.13
    POSITIVE LOGITS
     NO
    0.27
     yes
    0.26
     YES
    0.25
     Yes
    0.24
    yes
    0.24
    YES
    0.23
    NO
    0.20
     no
    0.19
    Yes
    0.19
    _NO
    0.19
    Act Density 0.052%

    No Known Activations