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

    Neuronpedia

    INDEX
    Explanations

    terms related to specific professions or fields of study

    oai_token-act-pair · gpt-3.5-turbo

    nouns and terms associated with specific subjects or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]).
    -0.65
    )).
    -0.63
    })
    -0.61
    iphate
    -0.59
    ))))
    -0.59
    '."
    -0.58
    swer
    -0.57
    ndum
    -0.57
    etsk
    -0.56
    ãĢĤ
    -0.56
    POSITIVE LOGITS
    pal
    0.62
     metaphors
    0.54
     explanations
    0.54
    ishly
    0.54
     capitals
    0.53
     versions
    0.52
     interpol
    0.52
    -,
    0.52
     fatigue
    0.52
     terminology
    0.51
    Act Density 1.179%

    No Known Activations