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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ambo
    -0.93
    abul
    -0.75
    tions
    -0.74
    ndra
    -0.72
    gb
    -0.71
    Operation
    -0.69
    aza
    -0.67
    ioned
    -0.67
    Grab
    -0.66
    Fore
    -0.66
    POSITIVE LOGITS
     brunt
    1.19
     plunge
    1.04
     reins
    1.01
     initiative
    0.98
     blame
    0.94
     guise
    0.89
     same
    0.88
     cues
    0.86
     liberty
    0.85
     heaviest
    0.85
    Act Density 0.056%

    No Known Activations