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

    Neuronpedia

    INDEX
    Explanations

    keywords related to background information or checks

    oai_token-act-pair · gpt-3.5-turbo

    references to background information or context in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nia
    -0.74
    erion
    -0.72
    abase
    -0.70
    nard
    -0.70
    emic
    -0.70
    eah
    -0.69
    enberg
    -0.69
    ikh
    -0.68
    ority
    -0.66
    ces
    -0.65
    POSITIVE LOGITS
     noise
    0.99
     checks
    0.96
     Checks
    0.83
    spection
    0.80
     background
    0.79
     radiation
    0.78
     check
    0.77
     music
    0.76
     backgrounds
    0.76
     noises
    0.74
    Act Density 0.057%

    No Known Activations