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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating permission and compliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sneaky
    -0.56
     tiny
    -0.56
    ῖς
    -0.55
     weirdly
    -0.51
    big
    -0.49
     nasty
    -0.48
     big
    -0.48
    Hej
    -0.48
     weird
    -0.47
    haha
    -0.47
    POSITIVE LOGITS
    ItemBackground
    0.86
    LEncoder
    0.70
    DebuggerNonUser
    0.66
     myſelf
    0.66
    XmlAccessType
    0.64
    bootstrapcdn
    0.63
     تضيفلها
    0.63
    Datuak
    0.63
    AddHtmlAttribute
    0.63
    isContained
    0.61
    Act Density 0.321%

    No Known Activations