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

    Neuronpedia

    INDEX
    Explanations

    frequent words related to expectation and updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uchen
    -0.17
    Æ°a
    -0.16
    меÑĤ
    -0.15
    ì§Ī
    -0.14
    rex
    -0.14
    çª
    -0.14
    illis
    -0.14
    åľŃ
    -0.14
    Reviewer
    -0.14
    ureau
    -0.14
    POSITIVE LOGITS
    orte
    0.17
    dera
    0.16
    ihan
    0.15
    ims
    0.15
    IMS
    0.15
    reau
    0.15
    è¾°
    0.15
    vat
    0.14
    agan
    0.14
    GMEM
    0.14
    Act Density 0.001%

    No Known Activations