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

    Neuronpedia

    INDEX
    Explanations

    references to backgrounds or background-related information

    oai_token-act-pair · gpt-3.5-turbo

    references to background information or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hab
    -0.82
    ikh
    -0.78
     WATCHED
    -0.74
    ishi
    -0.74
    icular
    -0.72
     Wend
    -0.71
     ILCS
    -0.68
    emin
    -0.66
    hap
    -0.66
    erion
    -0.66
    POSITIVE LOGITS
     background
    0.93
     Background
    0.87
     backgrounds
    0.87
     checks
    0.86
    coat
    0.80
     briefings
    0.78
     Checks
    0.78
     Investigations
    0.74
     trades
    0.72
     investigations
    0.70
    Act Density 0.012%

    No Known Activations