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

    Neuronpedia

    INDEX
    Explanations

    concepts related to choice and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isÃŃ
    -0.16
    ATAB
    -0.16
    ANJI
    -0.15
    theon
    -0.14
    uluk
    -0.14
     WaitForSeconds
    -0.14
    ÙĪØ«
    -0.14
    åĦĢ
    -0.13
    emax
    -0.13
     vet
    -0.13
    POSITIVE LOGITS
     feature
    0.22
    feature
    0.18
    Aspect
    0.18
     Aspect
    0.18
     Basis
    0.17
    essential
    0.17
    uet
    0.17
     BASIS
    0.17
     Feature
    0.17
     basis
    0.16
    Act Density 0.106%

    No Known Activations