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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks used in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zin
    -0.16
    otify
    -0.15
    emax
    -0.15
    anga
    -0.15
    liament
    -0.15
     Hüs
    -0.15
    á»ijc
    -0.14
    žÃŃ
    -0.14
    aukee
    -0.14
    |{↵
    -0.14
    POSITIVE LOGITS
    agram
    0.15
     communication
    0.15
    esson
    0.15
     scoop
    0.14
     s
    0.14
     Pon
    0.14
    urette
    0.14
    ory
    0.13
     properties
    0.13
    lán
    0.13
    Act Density 0.010%

    No Known Activations