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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "some" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    er
    -0.78
     cockroach
    -0.65
    crição
    -0.60
     Chry
    -0.60
     Kigali
    -0.59
    AutoScaleMode
    -0.59
    AfterClass
    -0.59
     LIABLE
    -0.58
     ruine
    -0.57
    ity
    -0.57
    POSITIVE LOGITS
    SOME
    1.40
     some
    1.29
     SOME
    1.24
    some
    1.14
    Some
    1.08
     SOM
    1.04
     Some
    1.03
    %")
    0.94
    SOM
    0.92
     Algunos
    0.91
    Act Density 0.149%

    No Known Activations