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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "say" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    letal
    -0.16
     synchron
    -0.16
    æį
    -0.15
    ijkstra
    -0.14
    chl
    -0.14
    raid
    -0.14
    thouse
    -0.14
    èŃ
    -0.14
    aller
    -0.14
    atk
    -0.14
    POSITIVE LOGITS
    MES
    0.15
    ings
    0.15
    -tm
    0.14
     Pods
    0.14
    .rc
    0.14
     Dit
    0.13
     MES
    0.13
    egis
    0.13
    iosis
    0.13
     nær
    0.13
    Act Density 0.030%

    No Known Activations