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

    Neuronpedia

    INDEX
    Explanations

    words related to transformation or change

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the process of changing or transforming something from one state or form to another

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    llah
    -0.78
     Cheong
    -0.70
     Administration
    -0.68
    Mah
    -0.67
    andr
    -0.65
     Anthem
    -0.65
     Limits
    -0.63
    Fram
    -0.63
    Discussion
    -0.63
     Seas
    -0.62
    POSITIVE LOGITS
    ibles
    1.08
     converts
    0.85
    verted
    0.84
    verting
    0.82
    itive
    0.77
    ible
    0.75
    ayne
    0.75
    rette
    0.74
     bapt
    0.73
    itional
    0.73
    Act Density 0.023%

    No Known Activations