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

    Neuronpedia

    INDEX
    Explanations

    the verb "be" in various constructions and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èĥ½å¤Ł
    -0.23
    èĥ½
    -0.19
     kunnen
    -0.17
    æķ¢
    -0.16
    amient
    -0.15
    anke
    -0.15
    anas
    -0.15
    robat
    -0.15
     kunne
    -0.15
     pouvoir
    -0.15
    POSITIVE LOGITS
     easily
    0.30
     Easily
    0.21
    ’t
    0.19
    opies
    0.19
     safely
    0.19
    adians
    0.18
    asily
    0.17
    adiens
    0.17
     readily
    0.17
    ister
    0.17
    Act Density 0.086%

    No Known Activations