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

    Neuronpedia

    INDEX
    Explanations

    proper names and characters in a fictional narrative

    oai_token-act-pair · gpt-3.5-turbo

    characters involved in dramatic or suspenseful situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Roberts
    -0.74
     Hyundai
    -0.72
     Myanmar
    -0.72
    Reviewer
    -0.72
    genre
    -0.67
    auts
    -0.67
     Kardash
    -0.67
    gency
    -0.66
    Fit
    -0.66
     Slovenia
    -0.65
    POSITIVE LOGITS
     convin
    1.00
     disgu
    0.97
     disguised
    0.94
     infiltrate
    0.94
     flashback
    0.92
     blackmail
    0.90
     discovers
    0.88
     treacher
    0.88
     Shinra
    0.88
     Luffy
    0.88
    Act Density 0.724%

    No Known Activations