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

    Neuronpedia

    INDEX
    Explanations

    references to cities and urban centers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ones
    -0.15
    OrFail
    -0.15
    iÄį
    -0.14
     multic
    -0.14
     peak
    -0.14
     Peak
    -0.14
     mismatch
    -0.14
     Honey
    -0.14
    isko
    -0.14
     Booker
    -0.14
    POSITIVE LOGITS
    ÏĨοÏģ
    0.17
    avenport
    0.17
    ength
    0.16
    ustain
    0.16
     WPARAM
    0.15
    olean
    0.15
    aversable
    0.15
     jinak
    0.14
    lbrace
    0.14
    loth
    0.14
    Act Density 0.015%

    No Known Activations