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

    Neuronpedia

    INDEX
    Explanations

    negative sentiment related to hopelessness or frustration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    ever or never

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rather
    -0.49
     autorytatywna
    -0.46
     leit
    -0.43
    Rather
    -0.42
     plutôt
    -0.42
     lobby
    -0.42
     solic
    -0.40
     Rather
    -0.40
    complexContent
    -0.38
    TEMPO
    -0.38
    POSITIVE LOGITS
    ValueStyle
    0.58
     jamás
    0.51
    永远
    0.51
     potranno
    0.49
     ooit
    0.48
     NEVER
    0.48
    httphttps
    0.47
    最快更新
    0.47
     forever
    0.47
    never
    0.47
    Act Density 0.027%

    No Known Activations