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

    Neuronpedia

    INDEX
    Explanations

    people's names intertwined with some kind of action

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names associated with political figures and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.74
    ghost
    -0.73
     Kinnikuman
    -0.72
    ibaba
    -0.67
    kB
    -0.67
    corruption
    -0.67
    ieve
    -0.67
    contact
    -0.65
    ahime
    -0.64
    iries
    -0.64
    POSITIVE LOGITS
     reiterated
    1.43
     added
    1.34
     emphasized
    1.34
     continued
    1.32
     contrasted
    1.30
     elaborated
    1.25
     clarified
    1.25
     stressed
    1.25
     echoed
    1.21
     insisted
    1.21
    Act Density 0.333%

    No Known Activations