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

    Neuronpedia

    INDEX
    Explanations

    mathematical queries related to values and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.63
     agrí
    -0.51
    Personensuche
    -0.48
     Vordergrund
    -0.45
     kaum
    -0.42
    Carriera
    -0.42
    setEditable
    -0.42
    designed
    -0.41
    IUrlHelper
    -0.41
     Perks
    -0.41
    POSITIVE LOGITS
     corresponding
    0.58
     mathematically
    0.57
    AndEndTag
    0.54
     represented
    0.54
     numerically
    0.54
     corresponds
    0.52
     equal
    0.52
     denoted
    0.51
     signified
    0.51
    corresponding
    0.50
    Act Density 1.958%

    No Known Activations