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

    Neuronpedia

    INDEX
    Explanations

    instances of emotional expressions and related narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Assembly
    -0.15
    _ASCII
    -0.13
    InputBorder
    -0.13
    å¬
    -0.13
    ASN
    -0.12
    adle
    -0.12
    ,},↵
    -0.12
     addCriterion
    -0.12
    igon
    -0.12
    ToDevice
    -0.12
    POSITIVE LOGITS
     as
    0.93
     как
    0.49
     als
    0.44
    	as
    0.43
     sebagai
    0.41
     καθÏİÏĤ
    0.40
    ä½ľä¸º
    0.38
     ÏīÏĤ
    0.35
     jako
    0.34
     while
    0.30
    Act Density 0.659%

    No Known Activations