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

    Neuronpedia

    INDEX
    Explanations

    negative expressions regarding personal beliefs or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ſelf
    -0.93
     iſt
    -0.88
     Houſe
    -0.87
     Efq
    -0.87
     ་་
    -0.85
     ſtate
    -0.82
     cauſe
    -0.81
     houſe
    -0.80
    phosa
    -0.80
     uſe
    -0.79
    POSITIVE LOGITS
    <eos>
    0.57
    +#+#
    0.57
     it
    0.54
    d
    0.52
    g
    0.50
    ↵↵
    0.48
    WebVitals
    0.47
    m
    0.46
    .
    0.46
    G
    0.46
    Act Density 0.403%

    No Known Activations