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

    Neuronpedia

    INDEX
    Explanations

    terms related to different modes or modalities of operation or approach

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elah
    -0.16
    lah
    -0.16
     Broad
    -0.16
    chine
    -0.16
    odom
    -0.15
    ãĤ¨ãĥ«
    -0.15
    ATO
    -0.14
    rient
    -0.14
     Fair
    -0.14
     Rub
    -0.13
    POSITIVE LOGITS
    unk
    0.16
    iveau
    0.16
    376
    0.15
    大åħ¨
    0.15
    redential
    0.14
    Äįin
    0.14
     }};↵
    0.14
    UNK
    0.14
    atti
    0.14
    anging
    0.14
    Act Density 0.006%

    No Known Activations