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

    Neuronpedia

    INDEX
    Explanations

    phrases related to applications or software

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "app" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EStreamFrame
    -0.77
     guiActiveUn
    -0.66
     sidx
    -0.66
    κ
    -0.63
     dive
    -0.63
     knots
    -0.62
     knot
    -0.62
     spit
    -0.61
    tymology
    -0.61
     maj
    -0.61
    POSITIVE LOGITS
    earance
    1.56
    ears
    1.33
    alach
    1.32
    ointment
    1.31
    lied
    1.27
    arently
    1.24
    earances
    1.23
    eared
    1.23
    arent
    1.14
    earing
    1.05
    Act Density 0.017%

    No Known Activations