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

    Neuronpedia

    INDEX
    Explanations

    significant nouns and verbs related to processes or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mass
    -0.16
    ird
    -0.16
    aphael
    -0.15
     ActionTypes
    -0.15
    estination
    -0.15
    |$
    -0.14
    OrFail
    -0.14
     surf
    -0.14
    unkt
    -0.14
     Rover
    -0.14
    POSITIVE LOGITS
    oft
    0.17
    aku
    0.15
    ारण
    0.15
    _IB
    0.14
    ember
    0.14
    526
    0.14
     Loads
    0.14
    ouden
    0.14
    theid
    0.13
     INTERVAL
    0.13
    Act Density 0.000%

    No Known Activations