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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating complexity or ambiguity in situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     TAMBÉM
    -0.55
     remp
    -0.53
     XNUMX
    -0.51
    cils
    -0.51
    اليا
    -0.50
    getRaw
    -0.49
    keyColumn
    -0.49
     autant
    -0.49
    StrictEqual
    -0.49
    égard
    -0.48
    POSITIVE LOGITS
    Somewhere
    1.38
     somewhere
    1.37
    somewhere
    1.31
     Somewhere
    1.28
     someplace
    1.23
     somehow
    1.11
    Somebody
    1.10
     something
    1.07
     Something
    1.06
    something
    1.04
    Act Density 0.228%

    No Known Activations