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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their associations in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Diwedd
    -0.69
     ostavi
    -0.65
    wixt
    -0.63
    énus
    -0.63
    ooga
    -0.62
     genoux
    -0.62
    aktur
    -0.61
    utched
    -0.61
    enuine
    -0.60
     Hesper
    -0.60
    POSITIVE LOGITS
    nisses
    0.53
    größern
    0.53
    Royce
    0.53
     araw
    0.52
    <blockquote>
    0.51
     Políticas
    0.51
     Quindi
    0.49
    roppo
    0.47
    EndInit
    0.47
     Darum
    0.47
    Act Density 0.067%

    No Known Activations