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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or locations followed by a symbol indicating a place, such as "St. John's âĢĻ"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character sequence 'âĢ' and related symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     epigen
    -0.77
     persistence
    -0.77
     synerg
    -0.77
     worms
    -0.76
     strategies
    -0.74
     genetically
    -0.73
     formula
    -0.73
     altru
    -0.73
     additive
    -0.72
     positives
    -0.72
    POSITIVE LOGITS
    University
    1.07
    where
    1.04
    localhost
    1.04
    stanbul
    1.03
    east
    1.02
    Northern
    1.00
    Los
    0.99
    ï¸
    0.99
    Brook
    0.98
    icago
    0.98
    Act Density 0.235%

    No Known Activations