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

    Neuronpedia

    INDEX
    Explanations

    references to individuals involved in various situations or incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONTAL
    -0.15
    when
    -0.15
     themselves
    -0.14
    lfw
    -0.14
    ,},↵
    -0.14
    _when
    -0.14
    ëĭĪê¹Į
    -0.13
    _contains
    -0.13
    å½ĵ
    -0.13
     aren
    -0.12
    POSITIVE LOGITS
     from
    0.34
     living
    0.31
     working
    0.30
     belonging
    0.30
     with
    0.27
     residing
    0.26
     operating
    0.25
     specializing
    0.25
     representing
    0.24
     wearing
    0.22
    Act Density 0.213%

    No Known Activations