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

    Neuronpedia

    INDEX
    Explanations

    phrases related to giving feedback or reviews

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote an overall assessment or evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.70
    ©¶æ
    -0.69
    RN
    -0.69
     Frie
    -0.67
    rogens
    -0.67
    Fax
    -0.66
     Caf
    -0.66
     Reborn
    -0.66
    cells
    -0.65
    ulic
    -0.65
    POSITIVE LOGITS
     picture
    0.93
     usefulness
    0.93
     satisfaction
    0.92
     length
    0.91
     attractiveness
    0.88
     effectiveness
    0.88
     direction
    0.87
     outlook
    0.86
     impression
    0.86
     tone
    0.85
    Act Density 0.033%

    No Known Activations