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

    Neuronpedia

    INDEX
    Explanations

    research-related phrases that indicate assessment, examination, or experimentation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    devils
    -0.45
     v
    -0.45
    iv
    -0.45
     in
    -0.42
     f
    -0.42
     Van
    -0.42
     Ro
    -0.41
     Y
    -0.40
     Mail
    -0.40
     geladeira
    -0.40
    POSITIVE LOGITS
    PerformLayout
    0.90
    Zeneca
    0.80
    ArrowToggle
    0.78
    ImageContext
    0.77
     circumcision
    0.76
     kaynağından
    0.76
    PDATE
    0.75
    Vidite
    0.75
    出版年
    0.75
    harapkan
    0.74
    Act Density 0.024%

    No Known Activations