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

    Neuronpedia

    INDEX
    Explanations

    terms related to adjustments and modifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "adjust" or "adjustment."

    np_acts-logits-general · gemini-2.0-flash

    adjusting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nene
    -0.62
    kaka
    -0.61
    нави
    -0.61
    (/\
    -0.61
    достатки
    -0.59
     Barker
    -0.59
    valho
    -0.58
     Na
    -0.58
     doInBackground
    -0.56
     Bateman
    -0.56
    POSITIVE LOGITS
     ADJUST
    1.30
     Adjust
    1.19
    Adjust
    1.19
     Adjusting
    1.13
     adjust
    1.12
     adjustments
    1.11
     adjusting
    1.11
     adjustment
    1.11
     Adjustment
    1.10
     adjusts
    1.08
    Act Density 0.111%

    No Known Activations