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

    Neuronpedia

    INDEX
    Explanations

    expressions that indicate hesitation or uncertainty in communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    auc
    -0.15
    IColor
    -0.14
    IGHT
    -0.14
    hausen
    -0.14
    ÅĻen
    -0.14
    али
    -0.14
    ight
    -0.14
    è¸
    -0.13
    EXTERN
    -0.13
    turned
    -0.13
    POSITIVE LOGITS
    andr
    0.16
    This
    0.15
     This
    0.14
    è¿Ļæĺ¯
    0.14
    éal
    0.14
    ested
    0.14
    _iface
    0.14
    rab
    0.14
     mang
    0.14
     probably
    0.13
    Act Density 0.097%

    No Known Activations