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

    Neuronpedia

    INDEX
    Explanations

    instances of dialogue and interaction in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ober
    -0.17
    æ®Ĭ
    -0.17
    ìĦĿ
    -0.17
    .training
    -0.17
     درب
    -0.16
    hari
    -0.16
    VICE
    -0.15
    udson
    -0.15
    νή
    -0.15
    akter
    -0.15
    POSITIVE LOGITS
     Pink
    0.17
     pink
    0.16
    aran
    0.15
    ars
    0.15
     fol
    0.15
     plat
    0.15
     Patch
    0.14
     creation
    0.14
     conf
    0.14
    igen
    0.14
    Act Density 0.007%

    No Known Activations