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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or hesitation in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     desapar
    -0.51
    Чыганаклар
    -0.45
     desplaz
    -0.43
     máme
    -0.43
     tryck
    -0.42
     alap
    -0.42
     verksamhet
    -0.42
     namelijk
    -0.42
     lentejuelas
    -0.42
    ặt
    -0.42
    POSITIVE LOGITS
     الحره
    0.81
    InjectAttribute
    0.76
    BeginContext
    0.75
     <=",
    0.74
    DoubleQuotes
    0.73
    tonsoft
    0.70
     isSet
    0.67
     pituitary
    0.66
    ThroughAttribute
    0.66
     webmaster
    0.65
    Act Density 0.123%

    No Known Activations