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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the process of revealing or disclosing information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lags
    -0.18
    gii
    -0.17
    	Copyright
    -0.17
    ccione
    -0.16
    ãĥ«ãĥķ
    -0.15
    izio
    -0.15
    ìĹħì²´
    -0.14
    uite
    -0.14
    profits
    -0.14
    ANEL
    -0.14
    POSITIVE LOGITS
    ing
    0.17
    ning
    0.15
    ia
    0.15
    (Un
    0.15
    eras
    0.15
    omatic
    0.15
    886
    0.14
    0.14
     Sou
    0.14
    mental
    0.14
    Act Density 0.039%

    No Known Activations