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

    Neuronpedia

    INDEX
    Explanations

    terms associated with consent or agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.86
    udeb
    -0.82
    sonian
    -0.77
    side
    -0.77
    CTV
    -0.76
    IRD
    -0.72
    BILITIES
    -0.72
    STON
    -0.70
    lake
    -0.70
    vertisement
    -0.68
    POSITIVE LOGITS
    acles
    0.95
    iates
    0.95
    ropy
    0.93
    iate
    0.93
    ucky
    0.90
    iated
    0.84
    ennial
    0.84
    rification
    0.83
    acle
    0.82
    acular
    0.82
    Act Density 0.019%

    No Known Activations