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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "to" in various contexts indicating intention or purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dying
    -0.69
    icipated
    -0.65
     slideshow
    -0.65
     CoC
    -0.64
     swearing
    -0.63
     Pledge
    -0.62
     liking
    -0.62
     nineteen
    -0.62
     risked
    -0.62
     barking
    -0.61
    POSITIVE LOGITS
    esville
    0.95
    pper
    0.87
    ilet
    0.81
     commemorate
    0.81
    ppers
    0.81
     differentiate
    0.80
     accommodate
    0.79
     enhance
    0.77
     replace
    0.76
    ixed
    0.75
    Act Density 0.147%

    No Known Activations