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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating decision-making and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oud
    -0.15
    apus
    -0.14
     åī
    -0.14
    apse
    -0.14
    ault
    -0.14
    &uuml
    -0.14
     ActionTypes
    -0.13
    yz
    -0.13
    _pes
    -0.13
    ulado
    -0.13
    POSITIVE LOGITS
    ãģ¾ãģļ
    0.31
     first
    0.28
     먼ìłĢ
    0.23
     First
    0.23
     basically
    0.22
    наÑĩала
    0.22
     åħĪ
    0.22
    åħĪ
    0.21
     ابتدا
    0.21
    first
    0.21
    Act Density 0.378%

    No Known Activations