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

    Neuronpedia

    INDEX
    Explanations

    phrases referring to influence and relationships in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ook
    -0.18
    picker
    -0.16
     Mach
    -0.15
    isse
    -0.15
    ooks
    -0.14
    essler
    -0.14
     mach
    -0.14
     bald
    -0.14
    ritten
    -0.13
    hawks
    -0.13
    POSITIVE LOGITS
    AGR
    0.18
    ahr
    0.17
    ipping
    0.16
    iyim
    0.16
    abo
    0.15
    ãĥ©ãĥĥãĤ¯
    0.15
    _blk
    0.14
    CES
    0.14
    AGO
    0.14
    neider
    0.14
    Act Density 0.128%

    No Known Activations