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

    Neuronpedia

    INDEX
    Explanations

    words related to mistakes or errors

    oai_token-act-pair · gpt-3.5-turbo

    words associated with mistakes or errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovy
    -0.70
    icrobial
    -0.68
    rogens
    -0.66
    ove
    -0.64
    mac
    -0.63
    rab
    -0.63
     crates
    -0.63
    grain
    -0.62
     Voc
    -0.61
    rollers
    -0.61
    POSITIVE LOGITS
     omission
    0.90
    OUS
    0.79
     perpetrated
    0.79
     involving
    0.76
    ously
    0.76
     happened
    0.72
     whereby
    0.71
    fulness
    0.70
    iasis
    0.70
    ful
    0.69
    Act Density 0.114%

    No Known Activations