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

    Neuronpedia

    INDEX
    Explanations

    references to actions and their descriptions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     незавершена
    -0.48
     TestBed
    -0.45
     Seventy
    -0.45
    ("~/
    -0.45
     seventy
    -0.44
    @@@@@
    -0.43
    Throughout
    -0.43
     Öffentlichkeit
    -0.43
     Kobayashi
    -0.42
     Humphreys
    -0.42
    POSITIVE LOGITS
     action
    1.38
     Action
    1.38
     ACTION
    1.34
    Action
    1.34
    action
    1.34
    getAction
    1.24
     Actions
    1.19
    IAction
    1.13
    ACTION
    1.11
     actions
    1.09
    Act Density 0.163%

    No Known Activations