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

    Neuronpedia

    INDEX
    Explanations

    powerful and forceful language

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to the importance of watching or paying attention to something notable or unique

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dylan
    -0.88
    stadt
    -0.76
     Zi
    -0.74
    toe
    -0.72
     Django
    -0.72
     Kath
    -0.72
    enhagen
    -0.71
     Pandora
    -0.71
     Chennai
    -0.70
     Caleb
    -0.69
    POSITIVE LOGITS
    Pros
    0.95
    arity
    0.92
    ĵ
    0.86
    Nob
    0.85
    active
    0.85
    esy
    0.85
    arma
    0.84
    ĵĺ
    0.83
     Noble
    0.83
    idable
    0.82
    Act Density 0.415%

    No Known Activations