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

    Neuronpedia

    INDEX
    Explanations

    dates and specific events within a narrative

    oai_token-act-pair · gpt-3.5-turbo

    references to specific days and years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    romeda
    -0.69
    egal
    -0.65
    pmwiki
    -0.63
    uch
    -0.61
     pse
    -0.60
    ovsky
    -0.58
    cro
    -0.57
    unic
    -0.57
     reuse
    -0.56
    pay
    -0.56
    POSITIVE LOGITS
     Newsweek
    0.76
     onwards
    0.76
    ,[
    0.74
    .[
    0.71
    reed
    0.71
     onward
    0.69
     alone
    0.68
    VERTISEMENT
    0.68
     Keane
    0.67
    .—
    0.66
    Act Density 0.098%

    No Known Activations