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 "changed" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isy
    -0.73
    glas
    -0.71
    mination
    -0.68
    hetical
    -0.64
    culosis
    -0.63
    bey
    -0.61
    zees
    -0.58
    uning
    -0.58
    ics
    -0.58
    weeney
    -0.57
    POSITIVE LOGITS
     drastically
    1.16
     radically
    1.12
     dramatically
    1.12
     hands
    1.02
     markedly
    0.94
     fundamentally
    0.93
     abruptly
    0.85
     substantially
    0.85
     significantly
    0.85
     direction
    0.83
    Act Density 0.057%

    No Known Activations