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

    Neuronpedia

    INDEX
    Explanations

    the word "some" and variations thereof in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.84
    lıyor
    -0.66
     Chry
    -0.65
     acido
    -0.65
    UnusedPrivate
    -0.61
     cockroach
    -0.60
    crição
    -0.57
     piatta
    -0.57
    ity
    -0.56
     opak
    -0.56
    POSITIVE LOGITS
    SOME
    1.25
     some
    1.17
     SOME
    1.11
    some
    1.07
     SOM
    1.03
    Some
    0.99
     Some
    0.96
    abetes
    0.90
    SOM
    0.86
    things
    0.84
    Act Density 0.150%

    No Known Activations