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

    Neuronpedia

    INDEX
    Explanations

    sections of text that indicate a list or summary format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.95
    ThroughAttribute
    -0.79
     gynhyrchwyd
    -0.78
    ConstraintMaker
    -0.77
     referenties
    -0.71
     ddelweddau
    -0.70
     ostavi
    -0.70
     '\\;'
    -0.70
    afficheront
    -0.69
     autorytatywna
    -0.69
    POSITIVE LOGITS
     some
    0.52
     what
    0.49
     eccl
    0.49
    StackNavigator
    0.49
     recev
    0.49
    cros
    0.48
     our
    0.48
     another
    0.47
    rami
    0.47
     commandement
    0.46
    Act Density 0.230%

    No Known Activations