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

    Neuronpedia

    INDEX
    Explanations

    numerical values or mathematical expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    userdetails
    -0.54
    andExpect
    -0.53
    цездатний
    -0.52
     doigt
    -0.52
     poitrine
    -0.49
     jól
    -0.48
     anges
    -0.47
     ensimmä
    -0.47
    stateMutability
    -0.47
     normaux
    -0.47
    POSITIVE LOGITS
    DockStyle
    0.68
    SuspendLayout
    0.68
     estekak
    0.66
    findpost
    0.64
    adaptiveStyles
    0.63
    bria
    0.60
     '\\;'
    0.59
    bitField
    0.58
     Brag
    0.58
    rungsseite
    0.58
    Act Density 0.018%

    No Known Activations