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

    Neuronpedia

    INDEX
    Explanations

    mathematical, statistical, and analytical terms

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to analysis and classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     to
    -0.67
     thereto
    -0.60
    To
    -0.57
    to
    -0.57
     TO
    -0.54
     To
    -0.51
    ModLoader
    -0.44
    externalActionCode
    -0.41
     toget
    -0.41
    Avg
    -0.40
    POSITIVE LOGITS
    natureconservancy
    0.42
    alien
    0.41
    my
    0.38
    pse
    0.38
    illery
    0.38
    gian
    0.37
    unciation
    0.36
    assuming
    0.36
    }{
    0.36
    ones
    0.36
    Act Density 1.469%

    No Known Activations