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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs and forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     have
    -0.82
     do
    -0.77
     put
    -0.77
     also
    -0.77
     set
    -0.75
     can
    -0.72
     
    -0.70
     be
    -0.69
     use
    -0.69
     get
    -0.69
    POSITIVE LOGITS
    parsedMessage
    1.51
    seems
    1.49
    seemed
    1.48
    wasn
    1.47
    happened
    1.46
    arrived
    1.44
    shall
    1.43
     ainfi
    1.42
    begins
    1.41
    follows
    1.41
    Act Density 0.748%

    No Known Activations