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

    Neuronpedia

    INDEX
    Explanations

    words related to accidents and incidents

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    thood
    -0.70
     ILCS
    -0.69
    Native
    -0.68
    avis
    -0.65
    zac
    -0.64
    racuse
    -0.62
     spons
    -0.59
    hemy
    -0.58
    Reviewer
    -0.58
     Flavoring
    -0.58
    POSITIVE LOGITS
     lasted
    1.51
     occurred
    1.31
     consisted
    1.23
     stemmed
    1.19
     happened
    1.17
     originated
    1.16
     ended
    1.15
     lasts
    1.14
     coincided
    1.14
     culmin
    1.13
    Act Density 0.337%

    No Known Activations