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

    Neuronpedia

    INDEX
    Explanations

    terms or phrases related to degrees of official status or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.98
    DockStyle
    -0.94
    RenderAtEndOf
    -0.94
     ―――――
    -0.89
     iſt
    -0.89
     ſy
    -0.89
    PhysRev
    -0.88
     الحره
    -0.87
    دانشنامهٔ
    -0.86
     AssemblyCulture
    -0.86
    POSITIVE LOGITS
     he
    0.71
     come
    0.66
    he
    0.65
     I
    0.65
     He
    0.65
     U
    0.64
     we
    0.64
     
    0.63
     other
    0.63
     not
    0.63
    Act Density 0.264%

    No Known Activations