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

    Neuronpedia

    INDEX
    Explanations

    dates or time-related information

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "This" or phrases indicating a specific time reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     srfAttach
    -0.76
     encour
    -0.73
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.70
    sic
    -0.69
     cryst
    -0.68
    forth
    -0.68
     externalToEVAOnly
    -0.67
    nown
    -0.67
    ledged
    -0.66
     accomp
    -0.63
    POSITIVE LOGITS
     Updated
    0.82
     Vegan
    0.81
    zbollah
    0.77
    Welcome
    0.75
     Wrestling
    0.75
     Wrest
    0.74
     Transcript
    0.73
    UFC
    0.71
     Expand
    0.70
     Subtle
    0.70
    Act Density 0.558%

    No Known Activations