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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation marks and brackets within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Goth
    -0.15
    áÄį
    -0.15
    odcast
    -0.15
    ede
    -0.15
    alse
    -0.14
    .cloudflare
    -0.14
    README
    -0.14
    elper
    -0.14
    ddy
    -0.14
    ãĤ¯ãĥŃ
    -0.14
    POSITIVE LOGITS
     citation
    0.27
     cita
    0.21
     needs
    0.20
    citation
    0.20
     clarification
    0.20
     needed
    0.19
    بØŃ
    0.18
     cite
    0.18
     citations
    0.18
     cit
    0.18
    Act Density 0.011%

    No Known Activations