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

    Neuronpedia

    INDEX
    Explanations

    phrases related to scheduling, planning, and preparation for events or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     afterwards
    -0.18
    arp
    -0.17
     afterward
    -0.17
     feedback
    -0.14
    ARP
    -0.14
    forcer
    -0.14
    ersion
    -0.14
     Nach
    -0.14
    -feedback
    -0.13
    eum
    -0.13
    POSITIVE LOGITS
     early
    0.32
    early
    0.29
    æĹ©
    0.28
     Early
    0.25
    Early
    0.25
     ahead
    0.24
     Ahead
    0.23
    Ahead
    0.23
    -ahead
    0.22
    .pre
    0.21
    Act Density 0.210%

    No Known Activations