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

    Neuronpedia

    INDEX
    Explanations

    terms related to hooks in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CHEMICAL
    -0.63
     Chemical
    -0.62
    "):
    -0.60
    parsedMessage
    -0.60
    зулта
    -0.60
    chemical
    -0.59
    Chemical
    -0.57
     indo
    -0.56
     Behavioral
    -0.56
     Epile
    -0.56
    POSITIVE LOGITS
     scandal
    0.80
     ethics
    0.78
    aba
    0.75
    nik
    0.72
    principalColumn
    0.69
    enderror
    0.67
    pacs
    0.67
     scandals
    0.66
    amo
    0.66
    onAttach
    0.64
    Act Density 0.049%

    No Known Activations