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

    Neuronpedia

    INDEX
    Explanations

    phrases related to positions and movements on a field

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    @student
    -0.08
     addCriterion
    -0.07
    radient
    -0.07
    hte
    -0.07
    eltas
    -0.07
    intree
    -0.07
    ixel
    -0.06
     kolo
    -0.06
    laz
    -0.06
    ζα
    -0.06
    POSITIVE LOGITS
    /right
    0.07
    side
    0.07
    ward
    0.07
    /left
    0.06
    è§Ĵ
    0.06
     aspect
    0.06
     corner
    0.06
     position
    0.06
     side
    0.06
    -side
    0.06
    Act Density 0.013%

    No Known Activations