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

    Neuronpedia

    INDEX
    Explanations

    different forms and expressions of the concept of variation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    efeller
    -0.18
    Carthy
    -0.17
    ister
    -0.17
    DonaldTrump
    -0.15
    ses
    -0.15
    ent
    -0.15
    iras
    -0.15
    ãĤĤãģĹ
    -0.15
    .nz
    -0.15
    verte
    -0.14
    POSITIVE LOGITS
    intl
    0.19
    degrees
    0.16
    ulist
    0.16
    ERTICAL
    0.16
    ulent
    0.16
    ÑĢоÑī
    0.15
    onymous
    0.15
    iances
    0.15
    ulence
    0.15
    poÄįet
    0.14
    Act Density 0.060%

    No Known Activations