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

    Neuronpedia

    INDEX
    Explanations

    terms related to thresholds and critical points in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DeltaTime
    -0.16
     Bauer
    -0.15
    kos
    -0.14
    empor
    -0.14
    conti
    -0.14
     Epic
    -0.14
    isoft
    -0.14
     epic
    -0.13
    fone
    -0.13
    acades
    -0.13
    POSITIVE LOGITS
     threshold
    0.26
     thresholds
    0.22
     Threshold
    0.22
    threshold
    0.21
    Threshold
    0.20
     thresh
    0.17
    ï¸
    0.17
    ìłIJ
    0.16
    anness
    0.16
    erras
    0.16
    Act Density 0.193%

    No Known Activations