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

    Neuronpedia

    INDEX
    Explanations

    references to novels and novel-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Berta
    -0.71
     popcorn
    -0.68
     Greta
    -0.67
     pij
    -0.67
     Ehren
    -0.65
     Eura
    -0.64
    Wheeler
    -0.64
    onka
    -0.63
    Revenir
    -0.62
    mura
    -0.62
    POSITIVE LOGITS
     Novel
    1.07
     NOVEL
    1.00
    SaveChangesAsync
    0.96
    Novel
    0.88
     Jarvis
    0.85
     peindre
    0.84
     voorbij
    0.84
    boBox
    0.84
     novel
    0.82
    theid
    0.81
    Act Density 0.087%

    No Known Activations