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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to publications and research metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    تدÙī
    -0.14
    arrow
    -0.14
    sWith
    -0.14
     Kear
    -0.14
    ooth
    -0.14
    ude
    -0.14
    chez
    -0.14
    rtle
    -0.14
    одав
    -0.13
    enberg
    -0.13
    POSITIVE LOGITS
    igham
    0.18
     latter
    0.16
    wide
    0.16
    apos
    0.16
    ways
    0.15
    nell
    0.15
    rait
    0.14
    indrome
    0.14
    unately
    0.14
    bilt
    0.14
    Act Density 0.090%

    No Known Activations