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

    Neuronpedia

    INDEX
    Explanations

    symbols or tokens related to formatting, particularly dates and times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ‌
    -0.60
     modem
    -0.57
     hood
    -0.56
    DataAnnotations
    -0.55
     Goodwill
    -0.54
     bode
    -0.54
     overhead
    -0.52
     benchmarks
    -0.52
     contingent
    -0.51
    ilot
    -0.51
    POSITIVE LOGITS
     desmotivaciones
    0.63
     ainfi
    0.62
     feroit
    0.60
    verwijspagina
    0.57
     évêque
    0.57
    AndEndTag
    0.57
     cuerdas
    0.56
     violación
    0.56
     decoracion
    0.56
    LookAnd
    0.55
    Act Density 0.577%

    No Known Activations