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

    Neuronpedia

    INDEX
    Explanations

    references to leadership or hierarchical roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enumii
    -0.62
    URLException
    -0.59
     mxArray
    -0.58
    Transkript
    -0.56
    ⁡
    -0.55
     дописавши
    -0.55
    istoitu
    -0.54
    ymce
    -0.53
    FirstResponder
    -0.52
     kiệm
    -0.50
    POSITIVE LOGITS
     head
    1.57
     HEAD
    1.55
     heads
    1.51
     Head
    1.50
    Head
    1.44
     Heads
    1.40
    head
    1.32
    HEAD
    1.28
     Kopf
    1.25
    Heads
    1.21
    Act Density 0.427%

    No Known Activations