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

    Neuronpedia

    INDEX
    Explanations

    patterns and relationships involving direction, movement, and color assignments

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     addCriterion
    -0.07
    ancock
    -0.06
    кеÑĤ
    -0.06
    airy
    -0.06
    jerne
    -0.06
     ìĥĪê¸Ģ
    -0.06
    impan
    -0.06
     Ire
    -0.06
    edio
    -0.06
    سة
    -0.06
    POSITIVE LOGITS
     determine
    0.10
     switches
    0.10
     determination
    0.10
     switch
    0.09
     determin
    0.09
     switching
    0.09
     determines
    0.09
     choose
    0.09
     determining
    0.09
     choice
    0.09
    Act Density 0.248%

    No Known Activations