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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Moreover" and other similar transition phrases

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     BoxFit
    -0.76
     оригіналу
    -0.74
    WebVitals
    -0.74
    EndContext
    -0.67
    s
    -0.66
    contentLoaded
    -0.64
    ke
    -0.62
    SourceChecksum
    -0.60
     Hit
    -0.59
    RRect
    -0.59
    POSITIVE LOGITS
    theless
    0.84
    amını
    0.74
    bibfield
    0.73
    Đặc
    0.73
    vency
    0.70
    ecture
    0.68
     lär
    0.68
    &+
    0.68
    Добавлено
    0.68
     Theſe
    0.68
    Act Density 0.019%

    No Known Activations