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

    Neuronpedia

    INDEX
    Explanations

    program or programming-related terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "pl"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĸ¬âĸ¬
    -0.63
     managerial
    -0.61
     Logged
    -0.61
    âĸ¬
    -0.60
    MI
    -0.60
    DEM
    -0.58
     Thousand
    -0.57
     Prof
    -0.56
     politically
    -0.56
    ³³³³³³³³³³³³³³³³
    -0.54
    POSITIVE LOGITS
    acement
    1.26
    asma
    1.25
    enty
    1.24
    ains
    1.18
    osion
    1.18
    oit
    1.17
    umbing
    1.15
    icable
    1.13
    icably
    1.12
    atinum
    1.10
    Act Density 0.021%

    No Known Activations