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

    Neuronpedia

    INDEX
    Explanations

    concepts related to programming functions and their behaviors

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     
    -0.54
     (
    -0.52
     &
    -0.52
    /
    -0.51
     y
    -0.50
     «
    -0.50
     All
    -0.49
     sort
    -0.49
    …
    -0.49
      
    -0.48
    POSITIVE LOGITS
     ―――――
    1.11
     Efq
    1.10
    ſelves
    1.09
    ſelf
    1.07
     Anſ
    1.07
     itſelf
    1.03
     ſind
    1.02
     Diſ
    1.02
     Theſe
    1.02
     poffible
    1.02
    Act Density 0.094%

    No Known Activations