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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "some" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مشين
    -0.77
     Offisielt
    -0.77
     parlant
    -0.76
     internetowa
    -0.74
    Vlastnosti
    -0.73
    arraycopy
    -0.73
    IonicModule
    -0.71
    Портал
    -0.71
     geslacht
    -0.70
    Jegy
    -0.69
    POSITIVE LOGITS
    some
    1.44
     some
    1.13
    Some
    1.09
    som
    1.00
     som
    0.97
     Some
    0.95
    SOME
    0.93
    Som
    0.88
     SOME
    0.88
    SOM
    0.85
    Act Density 0.164%

    No Known Activations