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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs indicating actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ford
    -0.15
    æĥij
    -0.15
    ead
    -0.15
    anned
    -0.14
    çļĦæĺ¯
    -0.14
    ally
    -0.14
    rosso
    -0.14
    ilda
    -0.14
    adel
    -0.13
    ically
    -0.13
    POSITIVE LOGITS
    /is
    0.35
    nt
    0.31
    htub
    0.18
    nts
    0.17
    NT
    0.17
    /w
    0.16
    zik
    0.16
     indeed
    0.15
    ìĬ´
    0.15
    ps
    0.15
    Act Density 0.442%

    No Known Activations