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

    Neuronpedia

    INDEX
    Explanations

    references to strength and power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ware
    -0.15
    ule
    -0.14
    ();)
    -0.14
    isser
    -0.14
     Unit
    -0.14
    æķ·
    -0.14
    _unit
    -0.14
    /default
    -0.14
    _IE
    -0.13
    ural
    -0.13
    POSITIVE LOGITS
    /Resources
    0.17
    ail
    0.17
    yles
    0.17
    à¸Ńะ
    0.17
    AIL
    0.16
    735
    0.15
    gent
    0.15
    BX
    0.15
    vg
    0.15
    AILS
    0.14
    Act Density 0.142%

    No Known Activations