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

    Neuronpedia

    INDEX
    Explanations

    words related to public announcements or declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ched
    -0.15
    ().'/
    -0.15
    iggins
    -0.15
    -ÑĤеÑħ
    -0.14
    nehmer
    -0.14
    hek
    -0.14
    ãĤŀ
    -0.14
    rale
    -0.14
     nonatomic
    -0.14
    cu
    -0.14
    POSITIVE LOGITS
     plans
    0.28
     Plans
    0.20
    plans
    0.19
     details
    0.18
    edly
    0.17
     intentions
    0.17
    ment
    0.16
    lug
    0.16
     intention
    0.16
     via
    0.16
    Act Density 0.023%

    No Known Activations