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

    Neuronpedia

    INDEX
    Explanations

    phrases suggesting uncertainty or conditionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adaptiveStyles
    -0.51
    SharedCtor
    -0.48
     мәкал
    -0.47
    әрмәләр
    -0.46
    HideFlags
    -0.44
    Autoritní
    -0.44
    desertcart
    -0.42
     Paglinawan
    -0.41
     Normdatei
    -0.41
    Rujuakan
    -0.41
    POSITIVE LOGITS
     also
    0.59
     de
    0.58
     dera
    0.56
    auri
    0.56
     için
    0.54
    noh
    0.54
    ARO
    0.53
    ında
    0.51
    MSA
    0.51
    <0x84>
    0.51
    Act Density 1.446%

    No Known Activations