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

    Neuronpedia

    INDEX
    Explanations

    terms indicating a decrease or reduction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    رشف
    -0.60
    Pautan
    -0.56
    +":
    -0.54
    StandardCharsets
    -0.53
    ThroughAttribute
    -0.52
    Unnamed
    -0.50
    balleur
    -0.50
    мум
    -0.49
    طبي
    -0.49
     Hor
    -0.48
    POSITIVE LOGITS
     reduction
    2.38
     reduced
    2.37
     decrease
    2.29
     decreased
    2.25
     reductions
    2.25
     decreasing
    2.21
     reducing
    2.17
     Reduction
    2.16
     Reduced
    2.15
     decreases
    2.15
    Act Density 0.172%

    No Known Activations