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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing individual contributions or relationships among people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     each
    -0.17
    riad
    -0.15
    edic
    -0.14
    anian
    -0.14
    Ù
    -0.14
    ks
    -0.14
    ric
    -0.14
    iverse
    -0.14
    atcher
    -0.14
    rian
    -0.14
    POSITIVE LOGITS
    ãĢħ
    0.19
    /all
    0.17
     respective
    0.17
     Nacht
    0.17
     successive
    0.16
    ting
    0.16
    ì¢ħ
    0.15
    others
    0.15
    strar
    0.15
    contre
    0.15
    Act Density 0.064%

    No Known Activations