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

    Neuronpedia

    INDEX
    Explanations

    references to actions and states of being in the past

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    past tense verb followed by noun or participle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CanadaChoose
    -0.42
    ſelves
    -0.40
    DockStyle
    -0.39
     faſt
    -0.35
     cromado
    -0.34
    Tikang
    -0.33
    ագրություններ
    -0.32
     Llew
    -0.31
     puesta
    -0.31
    WriteBarrier
    -0.31
    POSITIVE LOGITS
    encodeWith
    0.53
     informée
    0.50
    KindOfClass
    0.50
    Chham
    0.49
    delwed
    0.49
    TProtocol
    0.48
     contextLoads
    0.48
    UrlResolution
    0.48
    伏
    0.48
     ConstraintSet
    0.47
    Act Density 0.379%

    No Known Activations