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

    Neuronpedia

    INDEX
    Explanations

    specific copyright years

    oai_token-act-pair · gpt-3.5-turbo

    references to copyright notices and publication years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itiveness
    -0.64
     haunt
    -0.63
    phabet
    -0.63
    venge
    -0.62
    avorite
    -0.61
     blew
    -0.61
     qualify
    -0.60
    uls
    -0.59
    ivari
    -0.59
     rotation
    -0.59
    POSITIVE LOGITS
    20439
    1.03
    çīĪ
    0.87
    CHAT
    0.82
     Shutterstock
    0.79
     Burton
    0.75
    UTERS
    0.74
     Leah
    0.69
     ILCS
    0.68
    ForgeModLoader
    0.68
     STATS
    0.68
    Act Density 0.042%

    No Known Activations