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

    Neuronpedia

    INDEX
    Explanations

    references to military ranks and units

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilib
    -0.17
    adian
    -0.16
    оÑĤо
    -0.16
    odash
    -0.15
    odo
    -0.15
    ield
    -0.15
    ipi
    -0.15
    Łèĥ½
    -0.14
    ODO
    -0.14
    IER
    -0.14
    POSITIVE LOGITS
    hap
    0.14
     locally
    0.14
    ç´į
    0.14
    illes
    0.14
    alar
    0.14
    ham
    0.14
     Ritch
    0.14
    iro
    0.14
    bie
    0.14
     drag
    0.14
    Act Density 0.005%

    No Known Activations