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

    Neuronpedia

    INDEX
    Explanations

    interactions and dialogues between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Advisor
    -0.15
     Gra
    -0.15
    azzo
    -0.15
    antar
    -0.15
    _finalize
    -0.14
    zel
    -0.14
    linger
    -0.14
    çŃij
    -0.14
    ست
    -0.14
    agli
    -0.14
    POSITIVE LOGITS
    èģ
    0.15
     leisure
    0.15
     Nez
    0.15
     Din
    0.14
    ãi
    0.14
    romise
    0.14
     Shade
    0.14
    ains
    0.14
    충
    0.14
     physique
    0.13
    Act Density 0.302%

    No Known Activations