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

    Neuronpedia

    INDEX
    Explanations

    logical operators typically used in search queries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cheon
    -0.17
    é¨
    -0.17
    rello
    -0.16
    ŀ
    -0.16
    amber
    -0.15
    allee
    -0.15
     Garr
    -0.15
    нод
    -0.14
    _thickness
    -0.14
    é¡Į
    -0.14
    POSITIVE LOGITS
     Luc
    0.23
     luc
    0.22
    boost
    0.21
     boost
    0.21
     analy
    0.20
    Luc
    0.20
     Terms
    0.20
     Boost
    0.20
     boosting
    0.19
    ucene
    0.19
    Act Density 0.033%

    No Known Activations