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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating simplicity or ease

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mits
    -0.14
    anse
    -0.14
    ancia
    -0.14
    دÙĨ
    -0.14
    imensional
    -0.13
    pled
    -0.13
    ãģĻãģ¹ãģ¦
    -0.13
     PureComponent
    -0.13
    rient
    -0.13
     Paths
    -0.13
    POSITIVE LOGITS
    ening
    0.18
     dÃłng
    0.17
    /free
    0.16
    (er
    0.16
    /simple
    0.16
    buie
    0.15
    lington
    0.15
    easy
    0.15
    ily
    0.15
    ewood
    0.15
    Act Density 0.030%

    No Known Activations