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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal anecdotes or stories

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cheong
    -0.72
    andise
    -0.69
    iband
    -0.66
    rawdownloadcloneembedreportprint
    -0.66
    ufact
    -0.64
    olon
    -0.63
    enture
    -0.62
    emis
    -0.60
    que
    -0.59
    oru
    -0.59
    POSITIVE LOGITS
     guessed
    0.80
     fingers
    0.76
     unlikely
    0.70
     slim
    0.69
     damned
    0.66
     guesses
    0.66
     forgiven
    0.63
     Nine
    0.62
    senal
    0.62
    casters
    0.61
    Act Density 0.051%

    No Known Activations