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

    Neuronpedia

    INDEX
    Explanations

    capital letters followed by numbers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the letter "M" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yours
    -0.64
     Mechdragon
    -0.63
     Dispatch
    -0.62
     Belt
    -0.62
     validated
    -0.61
     blunt
    -0.61
     Celtic
    -0.61
     center
    -0.61
     solicitation
    -0.60
     Beyond
    -0.60
    POSITIVE LOGITS
    igrant
    1.18
    antle
    1.16
    astern
    1.15
    OST
    1.15
    ISSION
    1.14
    ONEY
    1.13
    ULT
    1.12
    ael
    1.12
    asks
    1.12
    ugg
    1.10
    Act Density 0.032%

    No Known Activations