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

    Neuronpedia

    INDEX
    Explanations

    concepts related to selflessness and the alleviation of suffering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emme
    -0.15
     Ritch
    -0.14
    abra
    -0.14
    ıklı
    -0.14
    itet
    -0.14
    Äĥr
    -0.13
    redo
    -0.13
     Surprise
    -0.13
    loor
    -0.13
    족
    -0.13
    POSITIVE LOGITS
     Tas
    0.17
     Fir
    0.17
    sla
    0.15
    acz
    0.15
     Fit
    0.14
     Observ
    0.13
    าà¸Ĭ
    0.13
     Conce
    0.13
    ÏĥÏĦο
    0.13
    éĶĭ
    0.13
    Act Density 0.020%

    No Known Activations