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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing uncertainty or existential reflections

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

    like they were liquid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PMailer
    -0.56
    Geografi
    -0.53
     identifiés
    -0.50
    zeczytaj
    -0.49
     surla
    -0.48
    ResumeLayout
    -0.48
    zzleHttp
    -0.48
     chrétienne
    -0.46
    paravant
    -0.46
     виправивши
    -0.46
    POSITIVE LOGITS
     EconPapers
    0.51
    CHICAGO
    0.40
     pres
    0.39
     MutableLiveData
    0.38
     ujednoznacz
    0.38
    🧍
    0.38
     PL
    0.37
    declare
    0.37
    ike
    0.36
    like
    0.36
    Act Density 0.013%

    No Known Activations