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

    Neuronpedia

    INDEX
    Explanations

    phrases related to changes or transformations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "changed" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mination
    -0.85
    zees
    -0.73
    glas
    -0.69
    isy
    -0.64
    zza
    -0.61
    amina
    -0.61
    swick
    -0.60
    stra
    -0.60
    erity
    -0.58
    sie
    -0.58
    POSITIVE LOGITS
     drastically
    1.06
     dramatically
    1.00
     radically
    0.97
     abruptly
    0.85
     materially
    0.83
     fundamentally
    0.80
     perceptions
    0.80
     hands
    0.80
     directions
    0.80
     direction
    0.79
    Act Density 0.067%

    No Known Activations