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

    Neuronpedia

    INDEX
    Explanations

    sentences that end with a full stop and contain common English words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    instances of strong emotional or impactful statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    boro
    -0.63
    ction
    -0.62
    hement
    -0.59
    uto
    -0.58
    ounce
    -0.58
    rad
    -0.56
    heit
    -0.55
    ings
    -0.53
    uca
    -0.52
    ades
    -0.51
    POSITIVE LOGITS
    ³³³³³³³³
    0.86
    ³³³
    0.81
    ³³³³³³³³³³³³³³³³
    0.76
    ³³³³
    0.72
    ????????
    0.65
    wcsstore
    0.62
    reditary
    0.62
    ↵Âł
    0.62
    inav
    0.60
    ONSORED
    0.59
    Act Density 0.675%

    No Known Activations