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

    Neuronpedia

    INDEX
    Explanations

    the structure of news articles

    oai_token-act-pair · gpt-3.5-turbo

    sequences of underscores or similar symbols, denoting sections or breaks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dynamics
    -0.76
     Instr
    -0.72
    ovan
    -0.71
     Myster
    -0.70
     Noir
    -0.70
     Diver
    -0.69
    oms
    -0.67
    ways
    -0.65
     Exile
    -0.65
     Vine
    -0.64
    POSITIVE LOGITS
    vu
    0.89
     ___
    0.82
    SOURCE
    0.81
    DOWN
    0.77
    HAEL
    0.76
    PLE
    0.75
    enhagen
    0.74
    kw
    0.71
    POS
    0.71
    quote
    0.68
    Act Density 0.017%

    No Known Activations