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

    Neuronpedia

    INDEX
    Explanations

    prepositions and their usage in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erv
    -0.19
    aho
    -0.15
     Macros
    -0.15
    ách
    -0.15
    abad
    -0.14
    ering
    -0.14
    mium
    -0.14
    icken
    -0.14
    aint
    -0.13
    ouden
    -0.13
    POSITIVE LOGITS
    ãĥĭãĥ¼
    0.17
    ãĥķãĥĪ
    0.15
     involved
    0.15
     tow
    0.15
     custody
    0.15
    hurst
    0.15
    umont
    0.14
     handy
    0.14
     possession
    0.14
     hand
    0.14
    Act Density 0.151%

    No Known Activations