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

    Neuronpedia

    INDEX
    Explanations

    numerical values, particularly those related to statistical data or measurements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    er
    -0.85
    <sub>
    -0.74
    <sup>
    -0.72
    en
    -0.70
    o
    -0.68
    aine
    -0.66
    TON
    -0.65
    y
    -0.65
    in
    -0.64
    ao
    -0.64
    POSITIVE LOGITS
    ConstraintMaker
    0.93
    NameInMap
    0.91
     StringField
    0.91
    nthesis
    0.86
      
    0.85
    citenamefont
    0.82
    DebuggerStep
    0.81
     putt
    0.80
    Philli
    0.79
     verschied
    0.79
    Act Density 0.003%

    No Known Activations