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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or events happening in the recent past

    oai_token-act-pair · gpt-3.5-turbo

    references to actions performed by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atever
    -0.60
     unforeseen
    -0.60
    anship
    -0.59
    zie
    -0.57
     allergies
    -0.56
    enei
    -0.56
    ''.
    -0.56
    idepress
    -0.55
    $.
    -0.55
    sort
    -0.55
    POSITIVE LOGITS
     above
    0.73
     presented
    0.69
     refers
    0.67
     represents
    0.64
     displayed
    0.61
     quoted
    0.60
    above
    0.60
    advertisement
    0.59
     hearing
    0.58
     contained
    0.58
    Act Density 0.379%

    No Known Activations