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

    Neuronpedia

    INDEX
    Explanations

    phrases that express judgment, accountability, and the complexities of human behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SBATCH
    -0.67
     &___
    -0.61
    nantes
    -0.60
    ength
    -0.58
    CCESS
    -0.57
     durata
    -0.56
    ORIA
    -0.56
     styr
    -0.55
     cáp
    -0.55
     strengthening
    -0.55
    POSITIVE LOGITS
     understandable
    0.54
     Dernière
    0.52
     MainAxisSize
    0.52
    AutoScaleMode
    0.50
     blame
    0.49
    _));
    0.46
     explanations
    0.45
    かわい
    0.45
    DockStyle
    0.44
    RAI
    0.44
    Act Density 0.279%

    No Known Activations