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

    Neuronpedia

    INDEX
    Explanations

    key events and announcements related to individuals' actions and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     critics
    -0.40
     Critics
    -0.39
     critic
    -0.37
    emples
    -0.36
     Critic
    -0.35
    ByExample
    -0.35
    Critic
    -0.34
     compara
    -0.33
    Critics
    -0.33
     crítica
    -0.33
    POSITIVE LOGITS
     announcement
    1.27
     announced
    1.07
     announcements
    1.05
     announce
    1.04
     Announcement
    1.00
     anúncio
    0.97
     ANNOUNC
    0.96
     announcing
    0.96
    宣布
    0.94
    Announcement
    0.93
    Act Density 0.464%

    No Known Activations