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

    Neuronpedia

    INDEX
    Explanations

    phrases related to functionality and effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.70
    tanleria
    -0.66
    +#+
    -0.64
    isContained
    -0.61
     Italijanski
    -0.57
    uxxxx
    -0.56
    protoimpl
    -0.54
    qrstuvwxyz
    -0.53
     становника
    -0.50
     indisponible
    -0.50
    POSITIVE LOGITS
     promised
    1.46
     advertised
    1.06
     promise
    1.04
     predicted
    1.02
     expected
    0.95
     pledged
    0.94
     promises
    0.93
     prome
    0.88
     anticipated
    0.88
     promessa
    0.85
    Act Density 0.315%

    No Known Activations