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

    Neuronpedia

    INDEX
    Explanations

    phrases related to being responsible or in control of a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bai
    -0.16
    eso
    -0.15
    //{{
    -0.15
    AXB
    -0.15
     OTHERWISE
    -0.14
    że
    -0.14
    orges
    -0.14
    pbs
    -0.14
    ãģĸ
    -0.14
    ils
    -0.13
    POSITIVE LOGITS
     Ad
    0.18
     deg
    0.16
    wheel
    0.15
     A
    0.15
    izi
    0.15
     recipro
    0.15
    athi
    0.14
    Impl
    0.14
    awei
    0.14
    sville
    0.14
    Act Density 0.006%

    No Known Activations