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

    Neuronpedia

    INDEX
    Explanations

    instances of leaving or departure in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orro
    -0.17
    Vect
    -0.15
    rete
    -0.15
    ulace
    -0.15
    anne
    -0.14
     sant
    -0.14
     Pod
    -0.14
     sana
    -0.14
    rious
    -0.13
    alars
    -0.13
    POSITIVE LOGITS
    ossa
    0.15
     Moff
    0.15
    ãĥªãĥ³
    0.14
    )?$
    0.14
     Sniper
    0.14
    ]-$
    0.14
    lyn
    0.14
    qi
    0.14
    agner
    0.14
    -addons
    0.14
    Act Density 0.331%

    No Known Activations