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

    Neuronpedia

    INDEX
    Explanations

    specific words related to spatial or directional terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èº
    -0.15
    hound
    -0.14
    лÑİб
    -0.14
    enco
    -0.14
     downtime
    -0.14
     obl
    -0.14
    rising
    -0.13
    наÑĩе
    -0.13
    ÑģÑĤи
    -0.13
    ego
    -0.12
    POSITIVE LOGITS
    /from
    0.18
    accom
    0.16
    zier
    0.16
    erm
    0.15
    /about
    0.15
    nic
    0.15
    getter
    0.15
    dl
    0.15
    tem
    0.15
     skl
    0.15
    Act Density 0.023%

    No Known Activations