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

    Neuronpedia

    INDEX
    Explanations

    terms related to library management or linking in programming contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     devoir
    -0.87
    
    -0.77
     pads
    -0.76
     vestiti
    -0.75
     pad
    -0.73
     grigio
    -0.72
    thral
    -0.71
     nyelv
    -0.71
    mel
    -0.70
    Best
    -0.69
    POSITIVE LOGITS
     LD
    1.48
    LD
    1.20
     ld
    1.07
     Ld
    0.91
    ld
    0.86
    ersham
    0.85
     Ald
    0.84
     Ters
    0.81
    ."</
    0.79
    Ald
    0.78
    Act Density 0.011%

    No Known Activations