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

    Neuronpedia

    INDEX
    Explanations

    various expressions and symbols of emotional sentiment and cultural significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ves
    -0.17
    825
    -0.16
    loub
    -0.15
    itori
    -0.14
    ditor
    -0.14
    tical
    -0.14
    olan
    -0.14
    umann
    -0.14
    enery
    -0.14
    enant
    -0.13
    POSITIVE LOGITS
    ãģĻãĤĭ
    0.28
     à¤ķरन
    0.23
     done
    0.22
     à¤ķरत
    0.22
     doing
    0.21
    doing
    0.21
    ãģĹãģŁ
    0.20
    done
    0.18
     ing
    0.17
     Doing
    0.17
    Act Density 0.002%

    No Known Activations