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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal opinions or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ñana
    -0.15
    ataka
    -0.15
     Tato
    -0.14
     Worlds
    -0.14
     ><?
    -0.13
    è¿Ļæł·çļĦ
    -0.13
    iy
    -0.13
    iddles
    -0.13
    anlık
    -0.13
     Click
    -0.13
    POSITIVE LOGITS
    alth
    0.18
     maybe
    0.17
    maybe
    0.17
     EDIT
    0.17
     personally
    0.16
     glad
    0.16
    ETA
    0.16
     dun
    0.16
    EDIT
    0.16
    ButtonItem
    0.16
    Act Density 0.487%

    No Known Activations