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

    Neuronpedia

    INDEX
    Explanations

    words or phrases related to frequency or repetition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ¾
    -0.16
     compromises
    -0.15
    å¤ĩ
    -0.15
    ROOM
    -0.15
    ÌĢ
    -0.14
    tracking
    -0.14
     kèm
    -0.14
    еж
    -0.14
    IRECTION
    -0.13
    room
    -0.13
    POSITIVE LOGITS
    ument
    0.19
    fr
    0.18
    -fr
    0.17
    ombat
    0.15
    onds
    0.15
    atz
    0.15
    eware
    0.15
    /fr
    0.15
    kin
    0.15
     FR
    0.15
    Act Density 0.116%

    No Known Activations