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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to notable figures or entities

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly in a context related to sports or entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Newt
    -0.70
    ktop
    -0.70
    itiveness
    -0.70
     HMS
    -0.69
     Sussex
    -0.69
    culosis
    -0.68
    terday
    -0.66
    PLIED
    -0.65
     Eliot
    -0.64
     Appalach
    -0.63
    POSITIVE LOGITS
    ondo
    0.91
    aldi
    0.89
    á
    0.89
    ña
    0.88
    acc
    0.85
    ello
    0.85
    acho
    0.83
    arez
    0.83
    uz
    0.82
    iro
    0.82
    Act Density 0.158%

    No Known Activations