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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "too" indicating excessiveness or limitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.86
    roves
    -0.79
     sement
    -0.79
     */;
    -0.76
    Kennedy
    -0.75
    }")
    -0.72
     Kirsch
    -0.71
    WireFormat
    -0.70
    ————————————
    -0.70
     invokingState
    -0.70
    POSITIVE LOGITS
     Too
    1.73
     too
    1.67
    too
    1.61
    Too
    1.61
     TOO
    1.59
    TOO
    1.53
     zbyt
    1.05
    troppo
    1.04
     太
    0.99
     allzu
    0.98
    Act Density 0.044%

    No Known Activations