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

    Neuronpedia

    INDEX
    Explanations

    edit-related text segments

    oai_token-act-pair · gpt-3.5-turbo

    references to media content or related editing notes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    $.
    -0.52
    âĵĺ
    -0.47
     respectively
    -0.45
    ).[
    -0.44
    ]."
    -0.44
    ''.
    -0.44
    ."[
    -0.43
    sylv
    -0.43
    }.
    -0.42
    .).
    -0.42
    POSITIVE LOGITS
    iple
    0.42
     QUEST
    0.42
    terness
    0.39
     misunderstand
    0.39
    enhagen
    0.37
     suspic
    0.36
    reenshots
    0.35
     GROUP
    0.34
     FANTASY
    0.34
    ccording
    0.33
    Act Density 10.187%

    No Known Activations