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

    Neuronpedia

    INDEX
    Explanations

    present tense forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aben
    -0.17
    chet
    -0.15
    etten
    -0.15
    uish
    -0.15
    βι
    -0.14
     Fach
    -0.14
    radan
    -0.14
    SKTOP
    -0.14
     rau
    -0.14
    ipay
    -0.13
    POSITIVE LOGITS
     expected
    0.28
     reportedly
    0.26
     understood
    0.26
     believed
    0.25
     reported
    0.25
     scheduled
    0.24
     final
    0.24
     eye
    0.24
     m
    0.23
     set
    0.23
    Act Density 0.094%

    No Known Activations