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

    Neuronpedia

    INDEX
    Explanations

    phrases related to causation or explanation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "Due to" indicating causation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abbling
    -0.74
     sheep
    -0.72
    adel
    -0.69
    amps
    -0.67
    joined
    -0.67
    amped
    -0.67
    enter
    -0.66
    aps
    -0.66
     jewels
    -0.64
    estern
    -0.63
    POSITIVE LOGITS
    chwitz
    0.75
     diligence
    0.75
    */(
    0.75
     simultane
    0.73
    math
    0.71
     dilig
    0.69
    cientious
    0.68
    endment
    0.68
    tesy
    0.67
     shortages
    0.66
    Act Density 0.010%

    No Known Activations