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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing discomfort or inability to cope with situations

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

    cannot endure or accept

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wach
    -0.43
    tières
    -0.42
    المكان
    -0.42
     Administrativna
    -0.41
     party
    -0.41
    HeaderText
    -0.39
     Taktlose
    -0.39
    ipient
    -0.39
     regulator
    -0.38
     pandemic
    -0.38
    POSITIVE LOGITS
    ThroughAttribute
    0.69
     désolés
    0.55
    fjspx
    0.52
    Bakgrunnsstoff
    0.51
    wendigkeit
    0.51
    Enllaces
    0.49
     AssemblyTitle
    0.48
     adoro
    0.48
    Hate
    0.45
     soportar
    0.45
    Act Density 0.012%

    No Known Activations