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

    Neuronpedia

    INDEX
    Explanations

    specific phrases that indicate a focus on objectives or purposes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kil
    -0.17
    usercontent
    -0.15
    actable
    -0.15
    tie
    -0.15
    jee
    -0.15
    mite
    -0.14
    ties
    -0.14
    eted
    -0.14
    272
    -0.14
    ikit
    -0.14
    POSITIVE LOGITS
    geries
    0.25
    bidden
    0.23
     sake
    0.21
    aging
    0.21
    -profit
    0.20
    /by
    0.19
     purposes
    0.19
     instance
    0.19
    feit
    0.17
    /about
    0.17
    Act Density 0.726%

    No Known Activations