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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific years or seasons

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     textual
    -0.64
    Plot
    -0.63
    abilia
    -0.63
    Entry
    -0.62
    Asia
    -0.61
    Software
    -0.60
    Maker
    -0.59
    Keys
    -0.59
    Notice
    -0.59
    itialized
    -0.58
    POSITIVE LOGITS
    âĢ²
    0.73
     marked
    0.68
    when
    0.67
     when
    0.66
     Dolphin
    0.63
    女
    0.62
     Oops
    0.62
     belonged
    0.61
     saw
    0.59
    ruary
    0.58
    Act Density 0.129%

    No Known Activations