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

    Neuronpedia

    INDEX
    Explanations

    instances of unique or significant contributions or changes over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Behavior
    -0.16
    avior
    -0.16
     Behavior
    -0.16
     behavior
    -0.15
    uisse
    -0.15
     honored
    -0.15
     colors
    -0.15
     afterward
    -0.14
    behavior
    -0.14
     labeling
    -0.14
    POSITIVE LOGITS
     heritage
    0.24
     cust
    0.23
     Heritage
    0.21
     conservation
    0.21
     urban
    0.20
    herit
    0.20
     Conservation
    0.19
     conserv
    0.19
     spatial
    0.19
     tangible
    0.18
    Act Density 0.000%

    No Known Activations