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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating possibility or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     may
    -0.38
    abstractmethod
    -0.33
     intptr
    -0.32
     Voss
    -0.32
     electro
    -0.31
     Hagen
    -0.31
    rungsseite
    -0.30
     custos
    -0.30
    may
    -0.29
     Keim
    -0.29
    POSITIVE LOGITS
    ſelves
    0.60
    resaid
    0.58
    <unused43>
    0.57
    Personensuche
    0.57
    <unused41>
    0.57
    <unused28>
    0.57
    <unused74>
    0.57
    <unused79>
    0.57
    <unused42>
    0.57
    <unused17>
    0.57
    Act Density 0.003%

    No Known Activations