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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate associations or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atically
    -0.17
    ırak
    -0.15
    ively
    -0.15
    chedulers
    -0.14
    μÏīÏĤ
    -0.13
    riends
    -0.13
    ird
    -0.13
    osa
    -0.13
    ensively
    -0.13
    DOC
    -0.13
    POSITIVE LOGITS
     each
    0.23
     most
    0.21
     emphasis
    0.20
     none
    0.19
     many
    0.19
     much
    0.19
     plenty
    0.18
    most
    0.18
     no
    0.18
     plans
    0.17
    Act Density 0.103%

    No Known Activations