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

    Neuronpedia

    INDEX
    Explanations

    instances of the word 'thus'

    oai_token-act-pair · gpt-3.5-turbo

    the word "thus" and its frequent usage in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kick
    -0.66
     Kl
    -0.64
     Metro
    -0.62
    rera
    -0.61
    ten
    -0.60
     Kelvin
    -0.59
     Williamson
    -0.58
     metro
    -0.57
     killer
    -0.57
     steroids
    -0.56
    POSITIVE LOGITS
    forth
    1.05
     guiActiveUn
    0.85
    mask
    0.84
    forward
    0.81
    bered
    0.81
    hiba
    0.77
    cedes
    0.74
    othe
    0.74
    phas
    0.74
    ================================================================
    0.74
    Act Density 0.016%

    No Known Activations