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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate possession or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ham
    -0.17
    illon
    -0.15
    unts
    -0.14
     Material
    -0.14
    fts
    -0.14
    wan
    -0.14
    ker
    -0.14
     Compatible
    -0.14
    -0.14
     and
    -0.14
    POSITIVE LOGITS
    eree
    0.17
    egov
    0.16
     eskort
    0.16
    \Bridge
    0.15
    aign
    0.14
     Needle
    0.14
    ãģĵãĤį
    0.14
    ersive
    0.14
    çĽĸ
    0.14
    olutely
    0.14
    Act Density 0.017%

    No Known Activations