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

    Neuronpedia

    INDEX
    Explanations

    phrases related to change or transformation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "transform" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     LIMITED
    -0.69
    PLIED
    -0.66
    olla
    -0.63
    Discussion
    -0.60
     Lists
    -0.60
    ramid
    -0.59
    xia
    -0.59
     Administration
    -0.59
     Reasons
    -0.58
     Examiner
    -0.57
    POSITIVE LOGITS
     transform
    1.01
    atile
    0.95
     transforms
    0.91
     transforming
    0.86
     transformations
    0.86
    ively
    0.86
     transformed
    0.85
     transformation
    0.85
    ational
    0.82
    amorph
    0.82
    Act Density 0.020%

    No Known Activations