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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating confusion or frustration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MotionEvent
    -0.16
    thinkable
    -0.15
    iaux
    -0.13
     ÐijоÑĢ
    -0.13
    ROTO
    -0.13
    èijī
    -0.13
     layoffs
    -0.13
    enga
    -0.13
    rac
    -0.12
     Solic
    -0.12
    POSITIVE LOGITS
     gold
    0.22
     chests
    0.21
     points
    0.21
     EXP
    0.20
     chest
    0.20
     coins
    0.19
     currency
    0.19
     platinum
    0.19
     XP
    0.19
     items
    0.19
    Act Density 0.217%

    No Known Activations