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

    Neuronpedia

    INDEX
    Explanations

    location names and proper nouns related to various contexts

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of places and characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.83
     characteristic
    -0.74
     thumbs
    -0.70
     combination
    -0.70
     liar
    -0.68
     omission
    -0.67
     imped
    -0.67
     accompanying
    -0.67
     workaround
    -0.64
     driver
    -0.64
    POSITIVE LOGITS
    Fest
    1.09
    topia
    0.98
     Street
    0.93
     Avenue
    0.91
    adelphia
    0.85
     Headquarters
    0.84
    opolis
    0.83
     Studios
    0.82
     Manor
    0.82
    FM
    0.81
    Act Density 0.529%

    No Known Activations