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

    Neuronpedia

    INDEX
    Explanations

    phrases related to pausing, noticing, and observing one's surroundings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Uploaded
    -0.16
    ounder
    -0.15
    егод
    -0.15
    ÄĻd
    -0.15
    kh
    -0.14
    ssi
    -0.14
     discharge
    -0.14
    iddi
    -0.14
    anked
    -0.14
    Wik
    -0.14
    POSITIVE LOGITS
    Rx
    0.16
    íݸ
    0.15
    _PICTURE
    0.15
    ãĥ«ãĥī
    0.15
    dy
    0.15
    Äį
    0.15
    elman
    0.15
    olas
    0.14
    690
    0.14
    _LAYER
    0.14
    Act Density 0.055%

    No Known Activations