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

    Neuronpedia

    INDEX
    Explanations

    the word "bot" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to bots and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Struct
    -0.67
     Statements
    -0.61
    egal
    -0.61
    ׾
    -0.59
    ournal
    -0.58
    ITED
    -0.58
     Situation
    -0.58
     Institution
    -0.58
    restricted
    -0.57
    IGH
    -0.57
    POSITIVE LOGITS
    anical
    1.19
    wana
    0.98
    anooga
    0.95
    herer
    0.94
    zeb
    0.90
     Clever
    0.86
    nets
    0.84
    leneck
    0.83
    any
    0.82
    cham
    0.81
    Act Density 0.012%

    No Known Activations