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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize or qualify belief or assertion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.80
     propOrder
    -0.61
    HtmlAttribute
    -0.59
    initComponents
    -0.58
     stället
    -0.56
     mukana
    -0.55
    Erfolge
    -0.54
     متحده
    -0.54
    InvalidProtocol
    -0.53
     vuotta
    -0.53
    POSITIVE LOGITS
     everyone
    0.83
     nobody
    0.76
     can
    0.75
     everybody
    0.75
     we
    0.74
     I
    0.72
     they
    0.72
     you
    0.71
     anyone
    0.70
     could
    0.68
    Act Density 0.256%

    No Known Activations