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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a tendency or inclination toward a particular action or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    teil
    -0.16
    imizer
    -0.16
    WebResponse
    -0.15
    achie
    -0.14
    ttp
    -0.14
    igrations
    -0.14
    ëĭ¹
    -0.14
    ЧеÑĢ
    -0.14
    еÑĢп
    -0.14
    ienda
    -0.14
    POSITIVE LOGITS
     toward
    0.21
    erness
    0.17
     towards
    0.17
    664
    0.15
     Burnett
    0.15
    olk
    0.14
     tend
    0.14
    ye
    0.14
     tends
    0.14
     speaking
    0.14
    Act Density 0.021%

    No Known Activations