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

    Neuronpedia

    INDEX
    Explanations

    question marks and their variations indicating uncertainty or inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouser
    -0.17
    idas
    -0.16
    pite
    -0.15
    .readValue
    -0.15
    Globals
    -0.15
    mart
    -0.15
    orer
    -0.15
    ohen
    -0.14
    ivr
    -0.14
     Demir
    -0.14
    POSITIVE LOGITS
    ling
    0.15
     заÑģÑĤ
    0.15
    bolt
    0.14
    eÄį
    0.14
    ORT
    0.14
    quam
    0.14
     cazzo
    0.14
    ÑĨи
    0.13
     Sexo
    0.13
     Canary
    0.13
    Act Density 0.009%

    No Known Activations