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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating necessity or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    needs to be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.53
    󠁴
    -0.52
    ☸
    -0.51
    midler
    -0.44
    berdayakan
    -0.43
    PMailer
    -0.43
     Wherefore
    -0.41
    tanleria
    -0.41
    věr
    -0.40
    thylamine
    -0.40
    POSITIVE LOGITS
     be
    0.58
     must
    0.53
    Enllaces
    0.49
     EA
    0.47
     dovre
    0.47
     needs
    0.47
    RTHOOK
    0.46
     Obrador
    0.46
     ba
    0.46
     doveva
    0.45
    Act Density 0.037%

    No Known Activations