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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating past experiences or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    able
    -0.19
     now
    -0.18
     currently
    -0.18
    conde
    -0.16
     hereby
    -0.16
    yah
    -0.16
    OMET
    -0.15
    ands
    -0.15
    currently
    -0.15
    dsn
    -0.15
    POSITIVE LOGITS
     originally
    0.28
    ness
    0.27
     hoped
    0.24
     earlier
    0.24
    nt
    0.23
    /is
    0.21
    Originally
    0.20
     Earlier
    0.20
    ron
    0.19
    origin
    0.18
    Act Density 0.129%

    No Known Activations