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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences describing accomplishments or achievements

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     psychiat
    -0.73
     landfall
    -0.68
     stray
    -0.67
     microbiome
    -0.66
     extinct
    -0.66
     preval
    -0.66
     slightest
    -0.66
     disarm
    -0.65
    urus
    -0.65
    flation
    -0.65
    POSITIVE LOGITS
     Together
    1.44
     Both
    1.28
     Neither
    1.08
     Their
    1.04
     He
    1.03
     According
    1.02
    Together
    1.01
     Though
    0.97
    Both
    0.97
     Later
    0.96
    Act Density 0.599%

    No Known Activations