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

    Neuronpedia

    INDEX
    Explanations

    content related to the design and purpose of various products and systems

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating design specifications or intended purposes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.84
    achus
    -0.72
     Warrant
    -0.70
    SPONSORED
    -0.70
    nown
    -0.69
     Unsure
    -0.68
    ahime
    -0.65
     Appears
    -0.62
     TAMADRA
    -0.62
    ifer
    -0.61
    POSITIVE LOGITS
    ueller
    0.77
    ertodd
    0.70
    DEBUG
    0.67
     secrecy
    0.62
     satir
    0.61
     mould
    0.60
    creen
    0.59
    aundering
    0.59
     shielding
    0.58
     parody
    0.57
    Act Density 0.191%

    No Known Activations