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

    Neuronpedia

    INDEX
    Explanations

    references to individuals and roles in narratives or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    teenth
    -0.21
    ses
    -0.18
    phans
    -0.18
    resse
    -0.18
    ımıza
    -0.17
    istra
    -0.17
    niest
    -0.17
    ials
    -0.17
    sembles
    -0.17
    panse
    -0.16
    POSITIVE LOGITS
    gether
    0.51
    linear
    0.49
    existent
    0.47
    neath
    0.45
    ductory
    0.45
    adecimal
    0.43
    selling
    0.42
    teen
    0.40
    west
    0.40
    etheless
    0.39
    Act Density 0.747%

    No Known Activations