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

    Neuronpedia

    INDEX
    Explanations

    temporal phrases and indicators of specific events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibox
    -0.15
     ward
    -0.14
     Pros
    -0.14
    lea
    -0.14
    adal
    -0.14
     Ward
    -0.14
    ãĤ
    -0.14
    691
    -0.13
     Imper
    -0.13
     posterior
    -0.13
    POSITIVE LOGITS
    íĹĪ
    0.16
     Hills
    0.16
    wie
    0.15
    phalt
    0.15
    .nz
    0.14
     ê¶ģ
    0.14
    ILLS
    0.14
    ENU
    0.14
    _NT
    0.13
    emu
    0.13
    Act Density 0.162%

    No Known Activations