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

    Neuronpedia

    INDEX
    Explanations

    instances of specific prepositions and conjunctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     æ®
    -0.14
    ãĥ¼ãĥ¬
    -0.14
    igar
    -0.14
     compass
    -0.13
    AFE
    -0.13
    /bar
    -0.13
    _union
    -0.13
    ug
    -0.13
    inge
    -0.13
    acea
    -0.13
    POSITIVE LOGITS
    utos
    0.16
     Breed
    0.15
    ascar
    0.15
    XObject
    0.14
    antes
    0.14
    iquer
    0.14
    eniable
    0.14
    zers
    0.14
    quet
    0.13
    ondon
    0.13
    Act Density 0.521%

    No Known Activations