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

    Neuronpedia

    INDEX
    Explanations

    adjectives that describe something as being very strong or powerful

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to subjective opinions and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ezek
    -0.76
    article
    -0.75
    Ä
    -0.74
    isi
    -0.74
    Camp
    -0.74
    Sche
    -0.71
    ocl
    -0.71
    kar
    -0.70
    isphere
    -0.70
    umar
    -0.70
    POSITIVE LOGITS
     bullish
    0.95
     rich
    0.93
     overpowered
    0.88
     bad
    0.88
     greedy
    0.85
     poor
    0.85
     lousy
    0.85
     harmless
    0.84
     badass
    0.84
     crappy
    0.84
    Act Density 0.488%

    No Known Activations