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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and expressions of frustration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ecies
    -0.15
    imus
    -0.15
    ollen
    -0.15
    asant
    -0.15
    átka
    -0.15
     Vander
    -0.15
    llen
    -0.14
     Meer
    -0.14
    .semantic
    -0.14
    entina
    -0.14
    POSITIVE LOGITS
     Osborne
    0.15
    trap
    0.15
     DOCUMENT
    0.14
     Encore
    0.14
     Closure
    0.14
     cst
    0.13
    sub
    0.13
    ament
    0.13
    hawk
    0.13
     sub
    0.13
    Act Density 0.000%

    No Known Activations