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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparisons in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    comparisons or contrasts between different subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CHAT
    -0.61
    akeru
    -0.60
    drive
    -0.59
     ______
    -0.58
     thanking
    -0.58
    ston
    -0.58
    èĢħ
    -0.58
     thanked
    -0.58
     Lust
    -0.57
    amo
    -0.57
    POSITIVE LOGITS
     counterparts
    0.79
     predecessors
    0.74
     ones
    0.72
     predec
    0.69
     averages
    0.65
     equivalents
    0.65
     rivals
    0.64
     predecessor
    0.63
    pees
    0.62
    oldemort
    0.61
    Act Density 0.818%

    No Known Activations