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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a detailed examination or analysis

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "look" in conjunction with various topics or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lette
    -0.73
    ievers
    -0.66
    glomer
    -0.64
    hes
    -0.64
    onna
    -0.63
    oct
    -0.62
    ickle
    -0.61
    gob
    -0.60
    iola
    -0.60
    sticks
    -0.60
    POSITIVE LOGITS
     whats
    1.03
     highlights
    0.83
     why
    0.77
     how
    0.77
     what
    0.71
     some
    0.68
     the
    0.63
     Wikipedia
    0.62
     finer
    0.62
     whence
    0.60
    Act Density 0.130%

    No Known Activations