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

    Neuronpedia

    INDEX
    Explanations

    comparisons of quality or effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emek
    -0.16
    amura
    -0.15
     Trojan
    -0.14
     OnTrigger
    -0.14
    ä»ģ
    -0.14
    umber
    -0.14
    abeth
    -0.14
    iff
    -0.14
    olor
    -0.14
     Ä°Åŀ
    -0.13
    POSITIVE LOGITS
    IRS
    0.18
     Fu
    0.16
     compared
    0.15
    kal
    0.15
     Boyd
    0.15
    ìĺģ
    0.14
    _Release
    0.14
     Cookbook
    0.14
    698
    0.13
    lt
    0.13
    Act Density 0.175%

    No Known Activations