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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and expressions of doubt or regret

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     itſelf
    -1.02
     Anſ
    -0.94
     pleaſure
    -0.93
     myſelf
    -0.88
     Majefty
    -0.85
     виправивши
    -0.84
     Jefus
    -0.83
     fhew
    -0.81
    enderror
    -0.79
     anſ
    -0.79
    POSITIVE LOGITS
     so
    0.54
     for
    0.53
     COVID
    0.52
     I
    0.50
     fact
    0.50
     COMPONENT
    0.49
    COVID
    0.47
     na
    0.47
    PyErr
    0.46
     che
    0.46
    Act Density 0.014%

    No Known Activations