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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating control or influence, particularly in decision-making contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ikh
    -0.16
    arn
    -0.16
    ieux
    -0.15
     therefore
    -0.15
    enic
    -0.14
    inand
    -0.14
     res
    -0.14
    adia
    -0.14
     hence
    -0.14
    SharedPointer
    -0.14
    POSITIVE LOGITS
    roker
    0.16
    itez
    0.15
    uff
    0.14
    θε
    0.14
    innen
    0.14
    thr
    0.14
    ahlen
    0.14
    653
    0.14
    opc
    0.14
    ero
    0.14
    Act Density 0.020%

    No Known Activations