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

    Neuronpedia

    INDEX
    Explanations

    instances of phrases related to interaction and playfulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.18
    wal
    -0.17
    çĦ
    -0.16
    ropoda
    -0.15
    RunWith
    -0.15
    kest
    -0.15
    inning
    -0.14
    æ¼ı
    -0.14
    UNET
    -0.14
     meas
    -0.13
    POSITIVE LOGITS
    itti
    0.17
     odds
    0.16
     Odds
    0.16
    ulace
    0.16
    æĪ
    0.16
    iso
    0.15
    agma
    0.14
     freely
    0.14
    eties
    0.14
    eson
    0.14
    Act Density 0.092%

    No Known Activations