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

    Neuronpedia

    INDEX
    Explanations

    words related to achieving or attaining something

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ROM
    -0.68
    SHIP
    -0.67
    hyde
    -0.65
    nia
    -0.65
    HAEL
    -0.63
    PDATE
    -0.63
     ATI
    -0.62
    meal
    -0.62
    hops
    -0.62
     Ferdinand
    -0.61
    POSITIVE LOGITS
    itudinal
    1.22
    uned
    1.19
    ension
    1.05
    uner
    1.04
    aining
    1.03
    uning
    1.03
    itud
    1.00
    itted
    0.96
    ments
    0.91
    atched
    0.91
    Act Density 0.017%

    No Known Activations