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

    Neuronpedia

    INDEX
    Explanations

    phrases related to digital interactions like tapping, scrolling, and digital display

    oai_token-act-pair · gpt-3.5-turbo

    terms related to technological functions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DCS
    -0.55
    azard
    -0.55
    ablishment
    -0.50
    ioxid
    -0.50
    dden
    -0.50
    Islamic
    -0.49
    appropriately
    -0.48
     è£ıç
    -0.47
    idden
    -0.47
    Islam
    -0.47
    POSITIVE LOGITS
     however
    1.00
     therefore
    0.80
     meanwhile
    0.77
     moreover
    0.75
     though
    0.71
     furthermore
    0.64
     also
    0.61
     ---------
    0.51
     thus
    0.51
     tho
    0.51
    Act Density 3.475%

    No Known Activations