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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "here."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rine
    -0.15
    minster
    -0.15
    ri
    -0.15
    roc
    -0.15
    anco
    -0.15
    tryside
    -0.14
     Woodward
    -0.14
    otate
    -0.14
    UNCH
    -0.14
    shot
    -0.14
    POSITIVE LOGITS
    æ±
    0.20
    after
    0.17
    ault
    0.17
    inkel
    0.17
    ίνα
    0.15
    fore
    0.15
    vation
    0.15
    ection
    0.14
    kening
    0.14
    ina
    0.14
    Act Density 0.055%

    No Known Activations