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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ensuring safety or security

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    EStreamFrame
    -0.75
    cffffcc
    -0.75
    question
    -0.75
     Cosponsors
    -0.74
    ãĤ»
    -0.69
    bling
    -0.68
    pmwiki
    -0.67
    esi
    -0.66
    oub
    -0.66
    PsyNetMessage
    -0.66
    POSITIVE LOGITS
    rity
    0.79
     everything
    0.76
     everyone
    0.76
     nobody
    0.71
     everybody
    0.70
     continuity
    0.68
     compliance
    0.68
     correctness
    0.68
     they
    0.68
     we
    0.68
    Act Density 0.624%

    No Known Activations