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

    Neuronpedia

    INDEX
    Explanations

    terms related to academic authority and source credibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ysa
    -0.15
    illisecond
    -0.15
    LETE
    -0.15
    eyse
    -0.15
    -git
    -0.15
    uliar
    -0.14
    olicit
    -0.14
    imli
    -0.13
     ÄĮer
    -0.13
    precated
    -0.13
    POSITIVE LOGITS
     ét
    0.24
     rac
    0.22
     sociedad
    0.22
     cultura
    0.21
     pens
    0.18
     teor
    0.18
     derechos
    0.18
     mundo
    0.18
     relaciones
    0.17
     civil
    0.17
    Act Density 0.044%

    No Known Activations