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

    Neuronpedia

    INDEX
    Explanations

    expressions related to creativity and trying new methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tap
    -0.15
    Äĥm
    -0.15
    ankind
    -0.15
     Gov
    -0.14
     MBA
    -0.13
    гов
    -0.13
     Pipes
    -0.13
     Linda
    -0.13
    lä
    -0.13
    plete
    -0.13
    POSITIVE LOGITS
     colleague
    0.19
     colleagues
    0.18
    ocab
    0.18
     Resource
    0.15
    illance
    0.14
     Planning
    0.14
    afs
    0.14
     teaching
    0.14
     planning
    0.14
     RESOURCE
    0.14
    Act Density 0.014%

    No Known Activations