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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "charming" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pii
    -0.15
    lenÃŃ
    -0.15
    ottie
    -0.14
    agara
    -0.14
    gie
    -0.14
     dán
    -0.14
    ifs
    -0.14
    piar
    -0.14
    å®Ļ
    -0.13
    _GE
    -0.13
    POSITIVE LOGITS
    kos
    0.16
    ly
    0.16
     Dix
    0.15
    mel
    0.15
     Lonely
    0.14
    AGO
    0.14
    okus
    0.14
    -less
    0.14
    kol
    0.13
    »
    0.13
    Act Density 0.002%

    No Known Activations