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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating loss or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ji
    -0.14
    xm
    -0.14
    енка
    -0.14
    ordes
    -0.14
    रत
    -0.13
    ãģķãĤĵ
    -0.13
    lesh
    -0.13
    inker
    -0.13
    _BC
    -0.13
    ismu
    -0.13
    POSITIVE LOGITS
     altogether
    0.29
     except
    0.28
     forever
    0.25
     leaving
    0.24
     replaced
    0.24
     entirely
    0.23
     completely
    0.23
    alto
    0.21
    except
    0.21
    æİī
    0.20
    Act Density 0.240%

    No Known Activations