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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "black" as in black box or black hole, often associated with mystery or concealment

    oai_token-act-pair · gpt-3.5-turbo

    references to "black" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PsyNetMessage
    -0.94
    ablishment
    -0.87
    igslist
    -0.83
    OPLE
    -0.82
    ICLE
    -0.82
    mble
    -0.78
    =-=-=-=-
    -0.77
     Lauder
    -0.76
    agall
    -0.76
    oldemort
    -0.74
    POSITIVE LOGITS
    smith
    1.22
    jack
    1.10
    berry
    1.07
    ened
    1.03
    bird
    0.97
    hawk
    0.96
    moon
    0.92
    horse
    0.91
    powder
    0.89
    beard
    0.88
    Act Density 0.037%

    No Known Activations