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

    Neuronpedia

    INDEX
    Explanations

    dates written in a date-month format

    oai_token-act-pair · gpt-3.5-turbo

    dates and times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ierrez
    -0.71
    anan
    -0.66
    cientious
    -0.65
    rider
    -0.63
    cies
    -0.63
    etimes
    -0.62
    emp
    -0.62
    ocl
    -0.61
    laim
    -0.60
    kef
    -0.60
    POSITIVE LOGITS
    east
    0.72
     coasts
    0.69
     onwards
    0.68
    Tokens
    0.64
     onward
    0.61
    banks
    0.60
    ilaterally
    0.60
     arrives
    0.60
    iann
    0.59
     riches
    0.59
    Act Density 0.175%

    No Known Activations