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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey the idea of expression or communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    纪
    -0.15
    idor
    -0.15
     Tough
    -0.14
    à¥ĩà¤ķर
    -0.13
    amma
    -0.13
    é¡ĶãĤĴ
    -0.13
    Schedulers
    -0.13
    asts
    -0.13
    ocol
    -0.12
    SystemService
    -0.12
    POSITIVE LOGITS
     speak
    0.42
     speaks
    0.42
     Speak
    0.36
     speaking
    0.35
     volumes
    0.34
     self
    0.33
    spe
    0.33
     Spe
    0.32
    Speak
    0.31
     spoke
    0.30
    Act Density 0.043%

    No Known Activations