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

    Neuronpedia

    INDEX
    Explanations

    video identifiers

    oai_token-act-pair · gpt-3.5-turbo

    references to videos and video-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tomb
    -0.69
     meanwhile
    -0.68
     orchestr
    -0.66
    ichick
    -0.65
     Tsukuyomi
    -0.61
     Nights
    -0.61
    ²
    -0.60
     orche
    -0.60
     Fortress
    -0.59
    uton
    -0.59
    POSITIVE LOGITS
    GREEN
    0.93
    Warning
    0.76
    CLE
    0.76
    DES
    0.75
    LOS
    0.73
    prev
    0.72
    EV
    0.72
    WARNING
    0.72
    VOL
    0.72
    Researchers
    0.72
    Act Density 0.133%

    No Known Activations