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

    Neuronpedia

    INDEX
    Explanations

    terms related to security and personal information protection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Circus
    -0.17
    quets
    -0.17
    isd
    -0.16
    quet
    -0.15
    ube
    -0.15
    enta
    -0.15
    harma
    -0.15
     SPDX
    -0.14
    imedia
    -0.14
    ursal
    -0.14
    POSITIVE LOGITS
     prompt
    0.16
     Prompt
    0.15
    ÑĪив
    0.14
     cof
    0.14
     Bulk
    0.14
     McInt
    0.14
    ãģ£ãģ±
    0.14
    ην
    0.14
    305
    0.14
     b
    0.14
    Act Density 0.039%

    No Known Activations