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

    Neuronpedia

    INDEX
    Explanations

    the verb "to be" in various tenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ford
    -0.15
    tti
    -0.14
    ories
    -0.14
    ibil
    -0.14
    ıs
    -0.13
    ivent
    -0.13
     åĨĨ
    -0.13
    ogn
    -0.13
    umeric
    -0.13
     maç
    -0.13
    POSITIVE LOGITS
    von
    0.18
    ephy
    0.16
    ood
    0.16
    æ¿Ł
    0.14
    ãĥĥãĥī
    0.14
     abroad
    0.14
    Interop
    0.14
    esium
    0.14
    nt
    0.14
    /if
    0.14
    Act Density 0.052%

    No Known Activations