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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significant change or improvement

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of transformation or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     LIMITED
    -0.72
    PLIED
    -0.66
    ramid
    -0.65
    xia
    -0.64
    olla
    -0.63
    REL
    -0.61
     Reasons
    -0.59
     prelim
    -0.59
     Administration
    -0.59
    foundation
    -0.58
    POSITIVE LOGITS
    atile
    0.92
     transform
    0.91
     transforms
    0.89
     transformations
    0.85
    ively
    0.83
     transformation
    0.79
    ational
    0.79
     transforming
    0.78
     transformed
    0.77
    amorph
    0.76
    Act Density 0.023%

    No Known Activations