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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "super" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sha
    -0.17
    side
    -0.16
    Degrees
    -0.16
    bury
    -0.16
    uche
    -0.15
    sworth
    -0.15
    ulses
    -0.15
    voor
    -0.15
    sl
    -0.14
    sla
    -0.14
    POSITIVE LOGITS
    ior
    0.27
    iors
    0.26
    ordinate
    0.26
    ieur
    0.25
    stit
    0.23
    IOR
    0.22
    intendent
    0.22
     super
    0.21
    iore
    0.21
    cil
    0.21
    Act Density 0.027%

    No Known Activations