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

    Neuronpedia

    INDEX
    Explanations

    requests for assistance or help

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by a request for help or a question

    np_acts-logits-general · gemini-2.0-flash

    asking for help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     odkazy
    -0.73
    Carriera
    -0.61
     invokingState
    -0.57
     AssemblyCulture
    -0.56
    HasAnnotation
    -0.55
     فريبيس
    -0.53
     LoggerFactory
    -0.52
    }}]{
    -0.51
    intenant
    -0.51
    ổi
    -0.51
    POSITIVE LOGITS
     someone
    3.85
    someone
    3.45
    Someone
    3.32
     Someone
    3.23
     somebody
    3.14
     SOMEONE
    2.79
    somebody
    2.78
     alguien
    2.70
     quelqu
    2.68
    Somebody
    2.61
    Act Density 0.486%

    No Known Activations