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

    Neuronpedia

    INDEX
    Explanations

    phrases that reference or emphasize a specific subject or idea

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.91
    ContentAsync
    -0.75
    MessageState
    -0.73
    ScopeManager
    -0.69
    AndEndTag
    -0.69
    RenderAtEndOf
    -0.69
    BagLayout
    -0.66
    tonsoft
    -0.65
     Efq
    -0.64
    OGND
    -0.63
    POSITIVE LOGITS
     is
    0.59
     happens
    0.58
     process
    0.58
    '
    0.56
     stance
    0.55
     I
    0.53
     concept
    0.52
    нін
    0.52
     ProtoMessage
    0.52
     you
    0.52
    Act Density 0.128%

    No Known Activations