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

    Neuronpedia

    INDEX
    Explanations

    expressions of degrees of intensity or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    #
    -0.15
     Moran
    -0.15
    urdy
    -0.15
     ModelState
    -0.14
    assis
    -0.14
     assignable
    -0.14
    رÙĪ
    -0.14
    質
    -0.14
    /posts
    -0.14
    abble
    -0.14
    POSITIVE LOGITS
    keit
    0.18
    uni
    0.16
    kup
    0.15
     equiv
    0.14
    ldr
    0.14
    veis
    0.14
    ůr
    0.14
     rein
    0.14
    ething
    0.13
    otto
    0.13
    Act Density 0.015%

    No Known Activations