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

    Neuronpedia

    INDEX
    Explanations

    significant words or phrases relating to actions and transformations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prop
    -0.17
    enes
    -0.16
    engin
    -0.15
    urette
    -0.15
    ène
    -0.15
    fu
    -0.15
    eros
    -0.15
    éĥ¨
    -0.14
     pointers
    -0.14
    377
    -0.14
    POSITIVE LOGITS
    ÑĨенÑĤÑĢа
    0.18
    ãģªãģĹ
    0.17
     Sev
    0.16
    egie
    0.15
    λε
    0.15
    ัà¸Ļว
    0.15
    @admin
    0.14
    ÃŃž
    0.14
    Transfer
    0.14
    íĺij
    0.14
    Act Density 0.022%

    No Known Activations