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

    Neuronpedia

    INDEX
    Explanations

    references to the word "all" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Various
    -0.20
    ugin
    -0.18
     Numerous
    -0.16
     various
    -0.16
    _firestore
    -0.16
     numerous
    -0.15
    าะ
    -0.15
    Various
    -0.15
     some
    -0.15
     somewhere
    -0.14
    POSITIVE LOGITS
     except
    0.27
     of
    0.27
    /all
    0.24
    Except
    0.24
    except
    0.23
     remaining
    0.22
     but
    0.22
    but
    0.20
     aspects
    0.20
     sorts
    0.20
    Act Density 0.121%

    No Known Activations