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

    Neuronpedia

    INDEX
    Explanations

    locations or settings where specific incidents or events occurred

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the occurrence and location of incidents or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orters
    -0.79
    ibles
    -0.76
    dds
    -0.75
    tan
    -0.73
    options
    -0.72
    okers
    -0.69
    orc
    -0.68
    igration
    -0.68
    izons
    -0.68
    ativity
    -0.67
    POSITIVE LOGITS
     Feb
    0.82
     Sept
    0.77
     Oct
    0.76
     April
    0.76
     Monday
    0.76
     spree
    0.76
     May
    0.74
     shortly
    0.74
     Nov
    0.73
     March
    0.71
    Act Density 0.164%

    No Known Activations