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

    Neuronpedia

    INDEX
    Explanations

    specific number phrases and keywords related to various topics

    oai_token-act-pair · gpt-3.5-turbo

    repetitive conjunctions or phrases indicating addition or continuity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Deal
    -0.68
    qt
    -0.64
    icc
    -0.63
    BIP
    -0.62
    imus
    -0.62
    brush
    -0.61
    spir
    -0.61
    Ĭ±
    -0.61
    FINE
    -0.60
    LinkedIn
    -0.60
    POSITIVE LOGITS
     secondly
    1.00
    romeda
    0.86
    rew
    0.83
    ersen
    0.82
     THEN
    0.79
     furthermore
    0.78
    hra
    0.78
    rogens
    0.74
     then
    0.72
    alus
    0.70
    Act Density 0.121%

    No Known Activations