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

    Neuronpedia

    INDEX
    Explanations

    directional terms and movement-related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acha
    -0.17
     navr
    -0.16
    kers
    -0.15
    dob
    -0.14
    olie
    -0.14
    ousand
    -0.14
    eland
    -0.14
    KER
    -0.14
    utral
    -0.14
    thood
    -0.14
    POSITIVE LOGITS
    wards
    0.18
    itches
    0.15
    911
    0.14
    LOCKS
    0.14
    AGMA
    0.14
    çe
    0.14
     Rap
    0.14
     пÑĥ
    0.14
    ward
    0.14
    幸
    0.13
    Act Density 0.061%

    No Known Activations