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

    Neuronpedia

    INDEX
    Explanations

    terms related to opinions and organizational entities like unions

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "opinion" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    weights
    -0.70
     floor
    -0.66
     fabrication
    -0.64
    ten
    -0.63
    abases
    -0.61
    \\\\\\\\\\\\\\\\
    -0.59
    cases
    -0.59
    ropolis
    -0.58
     WT
    -0.57
     Tanz
    -0.56
    POSITIVE LOGITS
    hip
    1.00
    piracy
    0.99
    pread
    0.98
    hips
    0.98
    ervatives
    0.97
    naire
    0.94
    hov
    0.94
    ervative
    0.93
    ystem
    0.92
    chool
    0.86
    Act Density 0.050%

    No Known Activations