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

    Neuronpedia

    INDEX
    Explanations

    technical instructions or computer-related terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    olen
    -0.67
    staking
    -0.65
    avers
    -0.64
    osponsors
    -0.64
     Originally
    -0.63
    uador
    -0.59
    ammers
    -0.58
    htaking
    -0.58
     Beware
    -0.57
    parser
    -0.57
    POSITIVE LOGITS
     entity
    0.83
     endeavor
    0.82
     figure
    0.80
     enclave
    0.78
     environment
    0.77
     institution
    0.77
     regimen
    0.75
     iteration
    0.75
     session
    0.75
     affair
    0.74
    Act Density 0.782%

    No Known Activations