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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases that discuss experiences or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GenerationType
    -0.55
    PerformLayout
    -0.46
     During
    -0.45
     Toujours
    -0.44
    During
    -0.42
     gyhoeddwyd
    -0.41
     sempre
    -0.41
     során
    -0.41
     TextAppearance
    -0.40
     during
    -0.40
    POSITIVE LOGITS
     getting
    1.08
     throwing
    1.02
     putting
    0.96
     pulling
    0.95
     installing
    0.94
     finding
    0.93
     quitting
    0.92
     doing
    0.92
     picking
    0.91
     buying
    0.91
    Act Density 0.763%

    No Known Activations