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

    Neuronpedia

    INDEX
    Explanations

    references to executives and leadership roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aka
    -0.19
    .xtext
    -0.17
    LETE
    -0.16
    IDA
    -0.16
    ร
    -0.15
    askan
    -0.15
    ings
    -0.15
    .LENGTH
    -0.15
    ida
    -0.14
    asso
    -0.14
    POSITIVE LOGITS
    ear
    0.16
    isable
    0.15
    uter
    0.15
    liner
    0.15
    aneously
    0.15
     quarters
    0.14
    eer
    0.14
    /compiler
    0.14
    zech
    0.14
    ally
    0.14
    Act Density 0.025%

    No Known Activations