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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negative situations or conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to difficult or distressing social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thens
    -0.48
    EVA
    -0.47
    isance
    -0.46
     expires
    -0.46
     lasts
    -0.46
    oola
    -0.46
     starred
    -0.44
    bye
    -0.44
    Mesh
    -0.44
    Loader
    -0.44
    POSITIVE LOGITS
     shortcomings
    0.59
     predicament
    0.58
     plight
    0.56
     unfolding
    0.55
     dangers
    0.55
     injust
    0.53
     antics
    0.52
     misconceptions
    0.52
     failings
    0.52
     pitfalls
    0.52
    Act Density 1.557%

    No Known Activations