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

    Neuronpedia

    INDEX
    Explanations

    negations and instances of doubt or uncertainty in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.78
    NameInMap
    -0.57
     "..\..\
    -0.56
    UnusedPrivate
    -0.53
     <=",
    -0.51
    antMatchers
    -0.50
    BindView
    -0.49
    Demografie
    -0.48
     utafitiHapana
    -0.45
    aronder
    -0.44
    POSITIVE LOGITS
     subtlety
    0.67
    ]--;
    0.67
     mince
    0.66
     surprise
    0.66
    GOTREF
    0.65
     surprises
    0.64
    iseite
    0.61
     Surprise
    0.61
     mystery
    0.60
    mistak
    0.60
    Act Density 0.302%

    No Known Activations