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

    Neuronpedia

    INDEX
    Explanations

    phrases related to understanding and mutual agreement in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iyi
    -0.14
     Intr
    -0.14
    enthal
    -0.14
     Rebels
    -0.14
    å²Ĺ
    -0.14
     intr
    -0.13
    vir
    -0.13
    EventListener
    -0.13
    رÙĬÙĥ
    -0.13
    hatt
    -0.13
    POSITIVE LOGITS
    clist
    0.18
    .setPosition
    0.17
    dech
    0.16
    etro
    0.15
    steller
    0.15
    .gz
    0.14
    лива
    0.14
     understandable
    0.14
    áÄį
    0.14
    FC
    0.13
    Act Density 0.055%

    No Known Activations