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

    Neuronpedia

    INDEX
    Explanations

    references to specific moments or instances in time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.65
     lifetimes
    -0.58
     morire
    -0.56
     Gonna
    -0.55
     riuscito
    -0.54
     chré
    -0.54
     Melhor
    -0.53
    วย
    -0.53
     démocr
    -0.53
    Different
    -0.52
    POSITIVE LOGITS
    Sucesor
    0.89
    URLException
    0.71
    μφωνα
    0.69
     obstante
    0.68
    Obrázky
    0.67
     particular
    0.67
    gatron
    0.67
    erdings
    0.66
     createState
    0.66
     '\\;'
    0.65
    Act Density 0.193%

    No Known Activations