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

    Neuronpedia

    INDEX
    Explanations

    words that denote inclusion or structural organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Containers
    -0.17
    uten
    -0.16
    -ÑĤо
    -0.16
    rams
    -0.16
    rang
    -0.15
    rap
    -0.15
    /company
    -0.15
    spm
    -0.14
    leg
    -0.14
    otic
    -0.14
    POSITIVE LOGITS
    -fluid
    0.24
    ments
    0.22
    ment
    0.20
    bridge
    0.17
    ément
    0.16
    editable
    0.16
    wealth
    0.15
    è²Į
    0.15
    folk
    0.15
    forth
    0.15
    Act Density 0.051%

    No Known Activations