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

    Neuronpedia

    INDEX
    Explanations

    phrases and constructions that emphasize comparison or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bulk
    -0.17
    eker
    -0.16
    yon
    -0.16
     Bulk
    -0.16
    icer
    -0.16
    bulk
    -0.15
    chten
    -0.15
    rient
    -0.14
    ality
    -0.14
     Lyon
    -0.14
    POSITIVE LOGITS
    stp
    0.16
     div
    0.16
    æ±½
    0.14
    gang
    0.14
    gtk
    0.14
    RPC
    0.14
     Stout
    0.14
    RegularExpression
    0.13
    410
    0.13
    onto
    0.13
    Act Density 0.015%

    No Known Activations