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

    Neuronpedia

    INDEX
    Explanations

    references to specific western geographical regions or directions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arness
    -0.17
    ầm
    -0.16
    oret
    -0.15
    uiten
    -0.15
    aign
    -0.14
    uteur
    -0.14
    vable
    -0.14
    istic
    -0.14
    hattan
    -0.14
    FINITE
    -0.14
    POSITIVE LOGITS
    most
    0.26
    ward
    0.21
    wards
    0.20
    minster
    0.19
     Indies
    0.18
    -most
    0.17
    burg
    0.17
    wind
    0.15
    ran
    0.15
    STA
    0.14
    Act Density 0.045%

    No Known Activations