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

    Neuronpedia

    INDEX
    Explanations

    instances of first-person narrative or opinions expressed in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     виправивши
    -1.08
     فريبيس
    -0.94
     transfieras
    -0.94
    ^(@)
    -0.91
     ProtoMessage
    -0.90
    GEBURTS
    -0.88
     snippetHide
    -0.86
     ivelany
    -0.85
     avoient
    -0.85
     متعلقه
    -0.84
    POSITIVE LOGITS
    i
    0.63
     I
    0.61
    b
    0.55
    j
    0.55
     
    0.53
    I
    0.51
    p
    0.50
    S
    0.48
     As
    0.48
    As
    0.47
    Act Density 0.142%

    No Known Activations