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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ramework
    -0.15
    isas
    -0.14
    phia
    -0.14
    istol
    -0.14
    еÑĢом
    -0.14
    ochen
    -0.13
    hani
    -0.13
    imus
    -0.13
     CreateTable
    -0.13
    oland
    -0.13
    POSITIVE LOGITS
     high
    0.81
     High
    0.66
    high
    0.61
    High
    0.54
    -high
    0.53
     HIGH
    0.52
     middle
    0.51
    _high
    0.47
    .high
    0.47
    HIGH
    0.46
    Act Density 0.479%

    No Known Activations