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

    Neuronpedia

    INDEX
    Explanations

    phrases that express doubt or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ç½²
    -0.16
    ENO
    -0.15
     Rencontre
    -0.15
    aju
    -0.14
    اة
    -0.14
    igin
    -0.13
    pressed
    -0.13
    bit
    -0.13
     vari
    -0.13
    Backing
    -0.13
    POSITIVE LOGITS
    ookies
    0.14
    osex
    0.14
    ouse
    0.14
     REST
    0.14
    landa
    0.13
    ousse
    0.13
    oose
    0.13
    791
    0.13
    å±ķ
    0.13
    _hdl
    0.13
    Act Density 0.168%

    No Known Activations