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

    Neuronpedia

    INDEX
    Explanations

    specific names or terms related to Darwin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hints
    -0.17
    pez
    -0.15
    oli
    -0.14
    vie
    -0.14
    roud
    -0.14
    ostel
    -0.14
    igid
    -0.14
    ersistent
    -0.13
    enti
    -0.13
    imon
    -0.13
    POSITIVE LOGITS
    abort
    0.17
    .toolbox
    0.15
    sworth
    0.15
    ichert
    0.14
    èĭ
    0.14
     Pact
    0.14
    erialize
    0.14
     Robbins
    0.14
    è
    0.13
    lac
    0.13
    Act Density 0.029%

    No Known Activations