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

    Neuronpedia

    INDEX
    Explanations

    instructions or reminders

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the importance of remembering or not forgetting something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hook
    -0.73
    elle
    -0.69
    folk
    -0.68
    framework
    -0.67
     wom
    -0.65
    cheat
    -0.65
    oreal
    -0.64
    ullah
    -0.64
    law
    -0.64
    Released
    -0.64
    POSITIVE LOGITS
    heny
    0.70
    vation
    0.64
     elbows
    0.63
     Fraz
    0.62
     additions
    0.62
     sweets
    0.62
    tainment
    0.60
    theless
    0.60
    pieces
    0.59
     classics
    0.58
    Act Density 0.025%

    No Known Activations