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

    Neuronpedia

    INDEX
    Explanations

    references to academic papers and discussions of research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ventures
    -0.15
    uars
    -0.14
    aghetti
    -0.14
    707
    -0.14
    loquent
    -0.13
     Tomorrow
    -0.13
    toPromise
    -0.13
     ÎĬ
    -0.13
    aniel
    -0.13
    iali
    -0.13
    POSITIVE LOGITS
     novel
    0.20
    Contrib
    0.17
     therefore
    0.17
    nov
    0.17
     motiv
    0.17
     presented
    0.17
     contributions
    0.16
     CONTRIBUT
    0.16
     Novel
    0.16
    contrib
    0.15
    Act Density 0.109%

    No Known Activations