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

    Neuronpedia

    INDEX
    Explanations

    inquiries or statements about goals and intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     revoir
    -0.62
     المعيارى
    -0.62
     Normdatei
    -0.58
    AccessorTable
    -0.56
     habet
    -0.56
     Hanford
    -0.50
     bogotá
    -0.50
     Magellan
    -0.49
     Agamemnon
    -0.49
     applau
    -0.49
    POSITIVE LOGITS
     desired
    0.66
     aim
    0.65
    InjectMocks
    0.64
     doInBackground
    0.62
     intended
    0.59
    Glej
    0.59
     aims
    0.58
    Intended
    0.58
    twimg
    0.58
    ISSE
    0.57
    Act Density 0.523%

    No Known Activations