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

    Neuronpedia

    INDEX
    Explanations

    French or Italian prepositions indicating location or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /or
    -0.16
    lander
    -0.15
    èĤ¯
    -0.14
    burg
    -0.14
    esub
    -0.14
    ectomy
    -0.14
    ekli
    -0.14
    acades
    -0.14
    land
    -0.13
    rello
    -0.13
    POSITIVE LOGITS
     same
    0.17
    ture
    0.17
    anja
    0.17
    itre
    0.16
    tas
    0.15
    ottle
    0.15
     latter
    0.15
     following
    0.14
     sum
    0.14
     likes
    0.14
    Act Density 0.018%

    No Known Activations