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

    Neuronpedia

    INDEX
    Explanations

    words related to databases and computer science concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to concepts of value, measurement, and classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tes
    -0.70
    Ay
    -0.70
    PDATE
    -0.66
    senal
    -0.65
    Awesome
    -0.65
    Happy
    -0.65
     favourites
    -0.63
    Had
    -0.62
    elin
    -0.60
     Glas
    -0.60
    POSITIVE LOGITS
     refers
    1.66
     consists
    1.44
     involves
    1.32
     entails
    1.30
     signifies
    1.29
     represents
    1.27
     implies
    1.26
     encompasses
    1.25
     denotes
    1.22
     comprises
    1.19
    Act Density 0.461%

    No Known Activations