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

    Neuronpedia

    INDEX
    Explanations

    variations and differences across different subjects or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     estekak
    -0.57
    >",
    -0.53
    Rhestr
    -0.52
     alternately
    -0.50
     contextLoads
    -0.48
    rrggbb
    -0.48
    altern
    -0.47
    ussian
    -0.47
    onOptions
    -0.47
     butts
    -0.47
    POSITIVE LOGITS
     across
    1.04
    across
    0.90
     between
    0.85
     Across
    0.83
     ACROSS
    0.82
    Across
    0.79
     among
    0.76
    between
    0.64
     amongst
    0.64
     regionally
    0.64
    Act Density 0.383%

    No Known Activations