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

    Neuronpedia

    INDEX
    Explanations

    reported speech and statements made by individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Pont
    -0.78
    2020
    -0.77
    pmwiki
    -0.73
    idelines
    -0.73
    align
    -0.72
    paralle
    -0.71
    otype
    -0.71
    crop
    -0.70
    ãĥ¯
    -0.70
    kun
    -0.70
    POSITIVE LOGITS
     afterward
    0.87
     remorse
    0.84
     goodbye
    0.84
     regrets
    0.78
     harrowing
    0.78
     afterwards
    0.77
     ordeal
    0.76
     angrily
    0.73
     she
    0.73
     he
    0.73
    Act Density 0.386%

    No Known Activations