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

    Neuronpedia

    INDEX
    Explanations

    words related to improvement and strengthening

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

    improving or changing something

    np_acts-logits-general · gemini-2.0-flash

    changing or existing states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ngdoc
    -0.47
    Jîn
    -0.47
    drawable
    -0.47
    randrange
    -0.46
    ByExample
    -0.44
     tộc
    -0.43
    toContain
    -0.43
    brenner
    -0.43
    从中
    -0.43
    あれば
    -0.42
    POSITIVE LOGITS
     existing
    1.09
    existing
    1.02
    Existing
    0.96
     bestehende
    0.96
     EXISTING
    0.94
    ValueStyle
    0.92
     Existing
    0.92
     istnie
    0.86
     preexisting
    0.84
     vorhand
    0.81
    Act Density 0.605%

    No Known Activations