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

    Neuronpedia

    INDEX
    Explanations

    terms related to measurements of altitude or performance relative to average values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    maz
    -0.19
    AIL
    -0.17
    puted
    -0.15
    laus
    -0.15
     Wet
    -0.15
    çĿ£
    -0.15
    ALLE
    -0.15
    exels
    -0.14
    ib
    -0.14
    dal
    -0.14
    POSITIVE LOGITS
    -normal
    0.25
     normal
    0.25
    normal
    0.25
    -average
    0.23
    Normal
    0.19
     par
    0.19
     average
    0.18
     Normal
    0.18
    æŃ£å¸¸
    0.18
     zero
    0.17
    Act Density 0.086%

    No Known Activations