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

    Neuronpedia

    INDEX
    Explanations

    key interactions involving requests or commands in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilon
    -0.20
    isas
    -0.16
    azu
    -0.14
    deserialize
    -0.14
    olum
    -0.13
    ungle
    -0.13
    frm
    -0.13
    ÑĢÑĮ
    -0.13
    isis
    -0.13
    iswa
    -0.13
    POSITIVE LOGITS
     older
    0.23
     elderly
    0.20
     middle
    0.20
     woman
    0.20
     women
    0.19
     uniform
    0.19
     suited
    0.19
     security
    0.18
    older
    0.18
     young
    0.17
    Act Density 0.342%

    No Known Activations