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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing surprise or amazement

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "I have never" indicating experiences that have not occurred

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uctions
    -0.67
    HP
    -0.66
     Reports
    -0.64
    Notes
    -0.63
    Copy
    -0.61
     Journals
    -0.61
    åĤ
    -0.60
     Towards
    -0.59
    DIT
    -0.58
     Pieces
    -0.58
    POSITIVE LOGITS
    theless
    1.10
    been
    1.08
     been
    1.05
     existed
    0.95
     EVER
    0.93
     tasted
    0.87
     Been
    0.86
     seen
    0.83
     heard
    0.83
     bothered
    0.82
    Act Density 0.041%

    No Known Activations