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

    Neuronpedia

    INDEX
    Explanations

    mentions of romantic relationships and commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abis
    -0.16
    èªī
    -0.15
    owitz
    -0.15
    ervas
    -0.15
    ream
    -0.15
    बल
    -0.14
     Stub
    -0.14
    alloc
    -0.14
    stral
    -0.14
    ικο
    -0.14
    POSITIVE LOGITS
     worst
    0.15
     ramp
    0.15
    ingt
    0.15
     dates
    0.15
     Benson
    0.14
    oot
    0.14
    Insn
    0.14
    lere
    0.13
    chwitz
    0.13
    wor
    0.13
    Act Density 0.025%

    No Known Activations