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

    Neuronpedia

    INDEX
    Explanations

    terms related to visual phenomena specifically focused on "float" and "symmetry."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    addContainerGap
    -0.45
    PYX
    -0.44
     Bukan
    -0.37
     başına
    -0.37
     establecimiento
    -0.36
     metast
    -0.35
     onlyOwner
    -0.34
    Popis
    -0.34
    Auswahl
    -0.34
    anasia
    -0.33
    POSITIVE LOGITS
     flo
    0.66
    rag
    0.64
    combin
    0.61
     distortion
    0.61
     floating
    0.59
     Flo
    0.59
     symmetry
    0.58
     combin
    0.58
     floats
    0.57
     Symmetric
    0.57
    Act Density 0.434%

    No Known Activations