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

    Neuronpedia

    INDEX
    Explanations

    contexts or phrases indicating conditions or considerations in specific situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     الحره
    -0.58
     trajets
    -0.57
    esistenza
    -0.56
    InstrumentedTest
    -0.55
    prüche
    -0.54
     betweenstory
    -0.52
     Biôgrafia
    -0.52
     Monfieur
    -0.51
    ThroughAttribute
    -0.50
    towych
    -0.50
    POSITIVE LOGITS
    ParallelGroup
    0.73
    EndContext
    0.69
    complexContent
    0.59
    ConstraintMaker
    0.59
    etheless
    0.58
    acyj
    0.57
    +#+
    0.56
    NOWLEDG
    0.55
    BeginContext
    0.55
    RTCF
    0.54
    Act Density 0.190%

    No Known Activations