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

    Neuronpedia

    INDEX
    Explanations

    LaTeX formatting elements used in mathematical expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     saites
    -0.96
     estimés
    -0.92
    TemporalType
    -0.88
    orsese
    -0.86
    phosa
    -0.84
    OGND
    -0.84
     Hasbro
    -0.82
    ագրություններ
    -0.81
    MemoryWarning
    -0.79
    UIControlState
    -0.79
    POSITIVE LOGITS
     =
    0.65
    =
    0.60
     +
    0.57
    +
    0.54
     Munt
    0.49
     tø
    0.48
    =&
    0.47
    >=</
    0.47
    фикси
    0.47
     E
    0.47
    Act Density 0.054%

    No Known Activations