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

    Neuronpedia

    INDEX
    Explanations

    references to elephants in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    elephant and mammoth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prawda
    -0.42
     liggen
    -0.41
     area
    -0.40
    area
    -0.40
    ratio
    -0.39
     outono
    -0.39
    ywna
    -0.38
    írito
    -0.38
    glBind
    -0.38
    bias
    -0.37
    POSITIVE LOGITS
     elephant
    1.36
     Elephant
    1.35
    Elephant
    1.34
     elephants
    1.34
     Elephants
    1.23
    elephant
    1.20
    phants
    1.09
     elefante
    1.07
     elef
    1.00
    🐘
    0.82
    Act Density 0.004%

    No Known Activations