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

    Neuronpedia

    INDEX
    Explanations

    discussions on the limitations and scope of research papers

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    StructEnd
    -0.56
     føl
    -0.55
     rodea
    -0.50
     Sociales
    -0.50
     виправивши
    -0.50
     stöd
    -0.49
    djangoproject
    -0.47
     Magnetism
    -0.47
    naar
    -0.47
    DataAnnotations
    -0.47
    POSITIVE LOGITS
     Suff
    0.76
    ⓧ
    0.67
     insuffisamment
    0.62
     Савезне
    0.61
    enumi
    0.60
     Bryant
    0.59
    InjectAttribute
    0.59
     himo
    0.58
    Suff
    0.58
     Cent
    0.57
    Act Density 0.359%

    No Known Activations