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

    Neuronpedia

    INDEX
    Explanations

    words related to stunning or shocking events

    oai_token-act-pair · gpt-3.5-turbo

    words associated with emotional impact or trauma

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Devi
    -0.77
     Laksh
    -0.70
    DragonMagazine
    -0.69
     Blaz
    -0.67
     Sum
    -0.67
     Alv
    -0.66
    devices
    -0.65
     Tsukuyomi
    -0.65
    Files
    -0.63
     Alb
    -0.63
    POSITIVE LOGITS
    uez
    0.82
    incial
    0.80
    ario
    0.80
    anamo
    0.72
    oshop
    0.72
    erker
    0.72
    EMENT
    0.70
    orian
    0.69
    ACA
    0.67
    edom
    0.67
    Act Density 0.000%

    No Known Activations