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

    Neuronpedia

    INDEX
    Explanations

    phrases that express personal opinions or preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orny
    -0.16
     zur
    -0.14
    adora
    -0.14
     Khu
    -0.14
    iglia
    -0.13
    inkel
    -0.13
    eway
    -0.13
    .toObject
    -0.13
    uib
    -0.13
     truly
    -0.13
    POSITIVE LOGITS
    opa
    0.15
     DERP
    0.14
    /=
    0.14
    å®ħ
    0.14
    plode
    0.14
    ernet
    0.14
    ippy
    0.14
     заболеваниÑı
    0.13
    ilik
    0.13
    Ñĥва
    0.13
    Act Density 0.697%

    No Known Activations