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

    Neuronpedia

    INDEX
    Explanations

    expressions of emphasis or intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å¦ĤæѤ
    -0.17
    ãĥ¼ãĥģ
    -0.15
    anca
    -0.15
    ï¼ĮåĽłä¸º
    -0.14
     xong
    -0.14
    croll
    -0.14
    ecret
    -0.14
    ownik
    -0.14
    idth
    -0.14
    BT
    -0.14
    POSITIVE LOGITS
     instead
    0.24
     maybe
    0.24
     it
    0.23
     there
    0.22
     perhaps
    0.21
     why
    0.21
     unless
    0.20
     imagine
    0.19
     although
    0.19
     while
    0.19
    Act Density 0.098%

    No Known Activations