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

    Neuronpedia

    INDEX
    Explanations

    neuronal noise and false positives, as it does not show consistent activation patterns for specific types of information in the provided text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of serious offenses and substantial events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     counting
    -0.69
     luck
    -0.66
     covenant
    -0.66
     ramps
    -0.65
     escal
    -0.64
     Deluxe
    -0.63
     star
    -0.63
     dolphin
    -0.63
     placement
    -0.62
     Crystal
    -0.62
    POSITIVE LOGITS
    RAW
    1.13
    Updated
    1.06
    Published
    1.03
    Advertisements
    1.01
    Cath
    0.98
    TOR
    0.98
    Associated
    0.96
    Thomas
    0.95
    Section
    0.95
    Posted
    0.95
    Act Density 0.279%

    No Known Activations