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

    Neuronpedia

    INDEX
    Explanations

    phrases about being part of an overarching project or campaign

    oai_token-act-pair · gpt-3.5-turbo

    references to broader campaigns or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     candles
    -0.68
     brakes
    -0.60
    ostics
    -0.60
    ostic
    -0.58
     sparks
    -0.58
     ok
    -0.58
     dodged
    -0.58
    acity
    -0.57
     slightest
    -0.57
     Tavern
    -0.56
    POSITIVE LOGITS
    ĸļ
    0.77
    ortment
    0.76
     circle
    0.75
    alloc
    0.73
    venture
    0.72
    "}],"
    0.71
    igsaw
    0.71
     consolidation
    0.70
     guiActiveUnfocused
    0.70
     folklore
    0.70
    Act Density 0.307%

    No Known Activations