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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the effectiveness or quality of experiences, actions, or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ufen
    -0.15
    ooter
    -0.14
    eka
    -0.14
     Todo
    -0.14
    iful
    -0.14
    lish
    -0.14
    legate
    -0.14
    dition
    -0.14
    hot
    -0.14
    esto
    -0.13
    POSITIVE LOGITS
     also
    0.20
    also
    0.15
    obus
    0.14
     aussi
    0.14
     .
    0.14
    ëıĦ
    0.14
     .↵↵
    0.14
    ebi
    0.14
     Also
    0.14
     Californ
    0.14
    Act Density 0.541%

    No Known Activations