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

    Neuronpedia

    INDEX
    Explanations

    references to legal or judicial matters

    oai_token-act-pair · gpt-3.5-turbo

    references to legal or judicial processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reunion
    -0.75
     Liberation
    -0.72
    phabet
    -0.72
    joy
    -0.71
    izons
    -0.69
    adel
    -0.66
     perman
    -0.65
     Adds
    -0.64
     Waves
    -0.63
     mosqu
    -0.63
    POSITIVE LOGITS
     wrong
    1.71
     mistake
    1.68
     incorrectly
    1.68
     inaccur
    1.64
     improperly
    1.64
     underest
    1.64
     wrongly
    1.63
     faulty
    1.60
     incorrect
    1.60
     misrepresent
    1.60
    Act Density 1.312%

    No Known Activations