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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences starting with "Every"

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to time periods and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amina
    -0.82
     Compatibility
    -0.67
    aye
    -0.67
    ahime
    -0.66
     disorderly
    -0.62
    waters
    -0.62
    qus
    -0.62
    ealous
    -0.60
     redes
    -0.60
    eworks
    -0.59
    POSITIVE LOGITS
     brings
    0.72
     publishes
    0.71
     lull
    0.70
     updates
    0.67
     invariably
    0.66
     headlines
    0.65
     lapse
    0.63
     inevitably
    0.62
    tick
    0.62
     dips
    0.62
    Act Density 0.259%

    No Known Activations