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

    Neuronpedia

    INDEX
    Explanations

    references to social interactions and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ofi
    -0.17
    ÅĤ
    -0.14
    lane
    -0.14
     mas
    -0.14
     eas
    -0.14
     exotic
    -0.14
    897
    -0.13
    705
    -0.13
    pen
    -0.13
    haps
    -0.13
    POSITIVE LOGITS
     Mention
    0.18
    mentioned
    0.17
    aden
    0.16
    unar
    0.16
    aea
    0.16
    ulty
    0.15
    alaxy
    0.15
    ozor
    0.15
    ripple
    0.15
    ittal
    0.14
    Act Density 0.132%

    No Known Activations