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

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions indicating similarity or preference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acco
    -0.16
    asca
    -0.16
    ses
    -0.16
    rou
    -0.16
    asco
    -0.15
    roe
    -0.15
    lio
    -0.14
    ãģ¹ãģį
    -0.14
    ,LOCATION
    -0.14
    ãģ¾ãģŁ
    -0.14
    POSITIVE LOGITS
    -minded
    0.37
     minded
    0.29
     unto
    0.29
     váºŃy
    0.25
    WISE
    0.24
    able
    0.24
     clock
    0.23
     nhau
    0.22
     wildfire
    0.20
    -wise
    0.20
    Act Density 0.095%

    No Known Activations