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

    Neuronpedia

    INDEX
    Explanations

    references to geometric planes or two-dimensional surfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EDEFAULT
    -1.10
     betweenstory
    -1.02
    NameInMap
    -0.95
    aarrggbb
    -0.89
     allAfrica
    -0.86
    قامة
    -0.83
     jeunesse
    -0.83
    -0.82
     Cuth
    -0.81
    AndEndTag
    -0.80
    POSITIVE LOGITS
     plane
    1.55
     planes
    1.51
     Plane
    1.49
     PLANE
    1.47
    plane
    1.47
    planes
    1.46
    Plane
    1.46
    Planes
    1.35
    PLANE
    1.34
     Planes
    1.27
    Act Density 0.089%

    No Known Activations