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

    Neuronpedia

    INDEX
    Explanations

    mentions of geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Black" and its contextual uses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DCS
    -0.98
    OPLE
    -0.94
    UTERS
    -0.89
    _-
    -0.87
    PsyNetMessage
    -0.87
    ablishment
    -0.82
    ICLE
    -0.81
    rative
    -0.79
    ATOR
    -0.78
    icular
    -0.78
    POSITIVE LOGITS
    berry
    1.24
    black
    1.07
     Panther
    0.99
    berries
    0.98
    smith
    0.97
    moon
    0.96
    Black
    0.95
     Black
    0.95
    hawk
    0.94
    jack
    0.93
    Act Density 0.015%

    No Known Activations