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

    Neuronpedia

    INDEX
    Explanations

    concepts related to abstract ideas or debates

    oai_token-act-pair · gpt-3.5-turbo

    themes related to irony, debate, and complex social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.71
     ç¥ŀ
    -0.65
     Dreams
    -0.64
    would
    -0.63
    OWS
    -0.61
    ares
    -0.61
     Picks
    -0.58
    ķ
    -0.58
    WARD
    -0.57
    ROR
    -0.57
    POSITIVE LOGITS
     lurking
    1.09
     involved
    1.04
     underway
    1.00
     happening
    0.97
     waiting
    0.97
     brewing
    0.97
     available
    0.96
     attached
    0.93
     everywhere
    0.93
     going
    0.89
    Act Density 0.286%

    No Known Activations