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

    Neuronpedia

    INDEX
    Explanations

    technical instructions or commands related to software operations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "will."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    engineering
    -0.76
    JD
    -0.70
    quished
    -0.66
    Said
    -0.65
     vocational
    -0.65
    ressing
    -0.63
    foreseen
    -0.62
    Enough
    -0.61
    hea
    -0.60
    MU
    -0.60
    POSITIVE LOGITS
     be
    1.22
     gladly
    1.14
     suffice
    1.09
     overwrite
    1.09
     appear
    1.06
     automatically
    1.05
     vary
    1.00
     disappear
    0.99
     ALWAYS
    0.97
     expire
    0.97
    Act Density 0.198%

    No Known Activations