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

    Neuronpedia

    INDEX
    Explanations

    references to geographical locations and movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Roberts
    -0.17
     Middleton
    -0.15
    æĥħ
    -0.14
    wind
    -0.14
    uzzle
    -0.14
    ujet
    -0.14
    yte
    -0.14
    Calibri
    -0.13
    cams
    -0.13
     Harding
    -0.13
    POSITIVE LOGITS
    erce
    0.18
    ickle
    0.17
    owler
    0.17
    ichel
    0.14
    tt
    0.14
    oso
    0.14
    åħĭ
    0.14
    ladu
    0.14
     Tiger
    0.14
    kle
    0.14
    Act Density 0.085%

    No Known Activations