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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve forms of the verb "to be" and conjunctions facilitating connections in complex sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iores
    -0.16
    heimer
    -0.15
     ern
    -0.14
    ono
    -0.14
    olina
    -0.14
    asic
    -0.14
    ÐŁÐļ
    -0.14
    uy
    -0.13
    achinery
    -0.13
    _SUPPLY
    -0.13
    POSITIVE LOGITS
    zos
    0.16
     {{↵
    0.16
    egrator
    0.15
    rogen
    0.15
     Hindered
    0.15
    urette
    0.15
    egend
    0.14
    adnÃŃ
    0.14
    engan
    0.14
    zed
    0.13
    Act Density 0.028%

    No Known Activations