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

    Neuronpedia

    INDEX
    Explanations

    phrases that encourage observation or reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ernel
    -0.16
    hait
    -0.15
    arter
    -0.14
    лаÑģ
    -0.14
    pent
    -0.14
    prit
    -0.14
    _ghost
    -0.13
    akens
    -0.13
    itters
    -0.13
    iale
    -0.13
    POSITIVE LOGITS
    ascar
    0.17
    oda
    0.15
    312
    0.14
    одÑĥ
    0.14
    amac
    0.14
     Solar
    0.14
    IPH
    0.14
     expressive
    0.13
    sut
    0.13
    anye
    0.13
    Act Density 0.070%

    No Known Activations