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

    Neuronpedia

    INDEX
    Explanations

    dates and events related to resignations

    oai_token-act-pair · gpt-3.5-turbo

    references to dates and numerical information related to events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.70
    lette
    -0.65
    risome
    -0.64
    ocations
    -0.63
    *:
    -0.63
    =-=-=-=-
    -0.62
    hide
    -0.60
    GS
    -0.59
    =(
    -0.59
     TOTAL
    -0.59
    POSITIVE LOGITS
     marking
    1.07
     sparking
    1.05
     pledging
    1.04
     shortly
    1.00
     joining
    0.96
     citing
    0.95
     replacing
    0.93
     announcing
    0.92
     thanking
    0.91
     prompting
    0.90
    Act Density 0.207%

    No Known Activations