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

    Neuronpedia

    INDEX
    Explanations

    years related to the publication of articles or research

    oai_token-act-pair · gpt-3.5-turbo

    copyright notices and publication dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tub
    -0.65
     impe
    -0.64
    venge
    -0.63
    avorite
    -0.63
     collapses
    -0.62
     blew
    -0.62
     disappear
    -0.61
     disadvant
    -0.61
    plain
    -0.60
     haunt
    -0.59
    POSITIVE LOGITS
    20439
    1.02
    å¹
    0.87
     STATS
    0.85
    çīĪ
    0.82
     "$:/
    0.75
     Burton
    0.73
    Creat
    0.73
    CHAT
    0.73
     SPACE
    0.70
    lins
    0.69
    Act Density 0.027%

    No Known Activations