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

    Neuronpedia

    INDEX
    Explanations

    negative assessments of entertainment experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upos
    -0.18
     Literal
    -0.15
    phas
    -0.15
    ÑģÑĤаÑĤи
    -0.15
    esel
    -0.15
    iar
    -0.14
    uled
    -0.14
    ran
    -0.14
    chn
    -0.14
     perfectly
    -0.14
    POSITIVE LOGITS
     WOW
    0.20
     memorable
    0.19
     exciting
    0.19
     anything
    0.19
     wow
    0.18
    revolution
    0.18
     excitement
    0.17
     groundbreaking
    0.17
    æľīä»Ģä¹Ī
    0.17
     either
    0.17
    Act Density 0.129%

    No Known Activations