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

    Neuronpedia

    INDEX
    Explanations

    imperative verbs related to commands or instructions

    oai_token-act-pair · gpt-3.5-turbo

    key action verbs and significant identifiers in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     captcha
    -0.64
     xp
    -0.64
    lining
    -0.63
     waivers
    -0.62
     Weston
    -0.60
     ));
    -0.60
     reliably
    -0.59
     overcrowd
    -0.59
     decl
    -0.57
     poaching
    -0.57
    POSITIVE LOGITS
    estine
    0.97
    %"
    0.96
    cellence
    0.94
    anmar
    0.86
    Zero
    0.85
    Flag
    0.83
    ghazi
    0.82
    ablishment
    0.82
    Gate
    0.81
    foundland
    0.80
    Act Density 0.275%

    No Known Activations