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

    Neuronpedia

    INDEX
    Explanations

    phrases that encourage communication or interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agh
    -0.15
    inand
    -0.15
    ifique
    -0.15
    iez
    -0.14
     compr
    -0.14
    ument
    -0.14
    ç±
    -0.14
    nar
    -0.14
    enen
    -0.14
    .named
    -0.14
    POSITIVE LOGITS
    ibel
    0.15
    allback
    0.14
    omit
    0.14
     ç¶
    0.14
    AVA
    0.14
    yne
    0.14
     Morales
    0.14
    ewise
    0.14
    thy
    0.14
    esi
    0.14
    Act Density 0.006%

    No Known Activations