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

    Neuronpedia

    INDEX
    Explanations

    expressions of disappointment or unmet expectations in character development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TEX
    -0.16
    853
    -0.15
    ẽ
    -0.15
    skyt
    -0.15
    dust
    -0.15
    ceae
    -0.15
    808
    -0.15
    antha
    -0.15
    ACHINE
    -0.14
    843
    -0.14
    POSITIVE LOGITS
     Dwight
    0.23
     Scr
    0.23
     Dund
    0.23
     Creed
    0.20
     Office
    0.20
     Pam
    0.20
     Abed
    0.20
     Branch
    0.19
     Jim
    0.19
     NBC
    0.19
    Act Density 0.004%

    No Known Activations