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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating the concept of unlocking or access

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

    unlocking features or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    évaluateur
    -0.43
    <blockquote>
    -0.41
     []:
    -0.39
    ie
    -0.39
    ad
    -0.37
    gwt
    -0.36
    Notae
    -0.35
    y
    -0.35
    ↵↵
    -0.35
    List
    -0.34
    POSITIVE LOGITS
     unlock
    2.06
     Unlock
    1.99
    Unlock
    1.94
     unlocked
    1.90
    unlock
    1.88
     unlocking
    1.77
     unlocks
    1.76
     Unlocked
    1.63
    UNLOCK
    1.56
    unlocked
    1.55
    Act Density 0.003%

    No Known Activations