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

    Neuronpedia

    INDEX
    Explanations

    references to military ranks or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otime
    -0.16
    vé
    -0.16
    ryn
    -0.16
     addCriterion
    -0.15
    icl
    -0.15
    hausen
    -0.15
    heit
    -0.15
    ób
    -0.15
    onet
    -0.15
     putas
    -0.15
    POSITIVE LOGITS
    -Col
    0.23
     colon
    0.20
    -col
    0.20
     Colonel
    0.17
     Commander
    0.17
    867
    0.17
    -command
    0.16
    enance
    0.16
    utenant
    0.16
    colon
    0.16
    Act Density 0.008%

    No Known Activations