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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or potential outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gazette
    -0.16
    rama
    -0.16
    ä¿
    -0.15
    rams
    -0.15
    Ĥ¹
    -0.14
    rak
    -0.14
     Budget
    -0.14
    éľĬ
    -0.14
    íļ¨
    -0.13
    _restrict
    -0.13
    POSITIVE LOGITS
     dece
    0.17
     poetic
    0.17
     academic
    0.17
    upe
    0.16
     vintage
    0.16
     feast
    0.15
     shaping
    0.15
    REAM
    0.15
     forget
    0.15
    èĩ£
    0.15
    Act Density 0.062%

    No Known Activations