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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "ung."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of "being awake" or "awareness."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¯ãĥ³
    -0.68
    cloth
    -0.64
    phia
    -0.64
    Ò
    -0.64
    Effective
    -0.63
    ICES
    -0.62
    IDER
    -0.62
    urity
    -0.62
    ques
    -0.61
    ãĥ¡
    -0.60
    POSITIVE LOGITS
    lasses
    1.33
    aroo
    1.02
    nir
    0.99
    regate
    0.98
    entle
    0.93
    oing
    0.91
    sten
    0.89
    sung
    0.87
    undo
    0.86
    sv
    0.85
    Act Density 0.035%

    No Known Activations