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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significant events or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Morg
    -0.17
    amm
    -0.15
    idon
    -0.14
     McGr
    -0.14
    iece
    -0.14
     applicable
    -0.14
     Trail
    -0.13
     Charlotte
    -0.13
     pal
    -0.13
    orman
    -0.13
    POSITIVE LOGITS
    lamaz
    0.16
    haar
    0.16
     Boeh
    0.16
    linger
    0.15
    alama
    0.15
    rita
    0.15
    /******/
    0.15
    chen
    0.14
    Fcn
    0.14
    arro
    0.14
    Act Density 0.086%

    No Known Activations