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

    Neuronpedia

    INDEX
    Explanations

    names of large animals, particularly focusing on specific species

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Vok
    -0.59
    ั่ว
    -0.56
     cock
    -0.55
    dob
    -0.55
     stocking
    -0.54
    credentials
    -0.53
    xie
    -0.53
    Thread
    -0.52
     deve
    -0.52
    Defaults
    -0.52
    POSITIVE LOGITS
     Elephants
    1.05
     tigers
    1.02
     lions
    0.98
     elephants
    0.97
     lion
    0.93
     elephant
    0.93
    elephant
    0.92
     tiger
    0.92
    Elephant
    0.92
     Elephant
    0.88
    Act Density 0.032%

    No Known Activations