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

    Neuronpedia

    INDEX
    Explanations

    possessive forms of the word "is" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    386
    -0.15
    ves
    -0.15
    roduced
    -0.15
    implicitly
    -0.14
    upa
    -0.14
    ulses
    -0.14
    bst
    -0.13
    lst
    -0.13
    796
    -0.13
    zte
    -0.13
    POSITIVE LOGITS
     been
    0.45
     Been
    0.37
    been
    0.37
    Been
    0.35
     BEEN
    0.33
     become
    0.26
     got
    0.25
     sido
    0.25
     gone
    0.20
     come
    0.20
    Act Density 0.107%

    No Known Activations