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

    Neuronpedia

    INDEX
    Explanations

    phrases that begin with "for" indicating purpose or reason

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.81
    MemoryWarning
    -0.80
    Autoritní
    -0.80
    GIVEREF
    -0.75
     Roskov
    -0.73
    Aktualisiert
    -0.72
    TagMode
    -0.71
    SequentialGroup
    -0.70
     '\\;'
    -0.70
    ensement
    -0.69
    POSITIVE LOGITS
    setupUi
    0.58
     Regarding
    0.55
    Regarding
    0.53
    โก
    0.52
     Other
    0.51
     касается
    0.50
     others
    0.50
     other
    0.49
     Others
    0.48
    Other
    0.48
    Act Density 0.129%

    No Known Activations